[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MB67DV08PGX4DPJXZZ3YJB":3,"skill-same:01M6MB67DV08PGX4DPJXZZ3YJB":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6MB67DV08PGX4DPJXZZ3YJB","sparse-autoencoder-training",null,"Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fsparse-autoencoder-training\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"training","sparse autoencoder training","superposition","when","features","for","Interpretability","Transformer","lens","neural network","saelens","feature","Evaluation","ml","Neural","decompose","use","discovery","Safety","network","analyzing","2026-11-10 10:12:30",false,"---\nname: sparse-autoencoder-training\ndescription: Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  category: ml-evaluation-and-safety\n  maintainer: Kalaris Labs\n  tags: Sparse Autoencoders, SAE, Mechanistic Interpretability, Feature Discovery, Superposition\n  dependencies: sae-lens>=6.0.0, transformer-lens>=2.0.0, torch>=2.0.0\n---\n\n# SAELens: Sparse Autoencoders for Mechanistic Interpretability\n\nSAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.\n\n**GitHub**: [jbloomAus\u002FSAELens](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens)\n\n## The Problem: Polysemanticity & Superposition\n\nIndividual neurons in neural networks are **polysemantic** - they activate in multiple, semantically distinct contexts. This happens because models use **superposition** to represent more features than they have neurons, making interpretability difficult.\n\n**SAEs solve this** by decomposing dense activations into sparse, monosemantic features - typically only a small number of features activate for any given input, and each feature corresponds to an interpretable concept.\n\n## When to Use SAELens\n\n**Use SAELens when you need to:**\n- Discover interpretable features in model activations\n- Understand what concepts a model has learned\n- Study superposition and feature geometry\n- Perform feature-based steering or ablation\n- Analyze safety-relevant features (deception, bias, harmful content)\n\n**Consider alternatives when:**\n- You need basic activation analysis → Use **TransformerLens** directly\n- You want causal intervention experiments → Use **pyvene** or **TransformerLens**\n- You need production steering → Consider direct activation engineering\n\n## Installation\n\n```bash\npip install sae-lens\n```\n\nRequirements: Python 3.10+, transformer-lens>=2.0.0\n\n## Core Concepts\n\n### What SAEs Learn\n\nSAEs are trained to reconstruct model activations through a sparse bottleneck:\n\n```\nInput Activation → Encoder → Sparse Features → Decoder → Reconstructed Activation\n    (d_model)       ↓        (d_sae >> d_model)    ↓         (d_model)\n                 sparsity                      reconstruction\n                 penalty                          loss\n```\n\n**Loss Function**: `MSE(original, reconstructed) + L1_coefficient × L1(features)`\n\n### Key Validation (Anthropic Research)\n\nIn \"Towards Monosemanticity\", human evaluators found **70% of SAE features genuinely interpretable**. Features discovered include:\n- DNA sequences, legal language, HTTP requests\n- Hebrew text, nutrition statements, code syntax\n- Sentiment, named entities, grammatical structures\n\n## Workflow 1: Loading and Analyzing Pre-trained SAEs\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\n\n# 1. Load model and pre-trained SAE\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, cfg_dict, sparsity = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# 2. Get model activations\ntokens = model.to_tokens(\"The capital of France is Paris\")\n_, cache = model.run_with_cache(tokens)\nactivations = cache[\"resid_pre\", 8]  # [batch, pos, d_model]\n\n# 3. Encode to SAE features\nsae_features = sae.encode(activations)  # [batch, pos, d_sae]\nprint(f\"Active features: {(sae_features > 0).sum()}\")\n\n# 4. Find top features for each position\nfor pos in range(tokens.shape[1]):\n    top_features = sae_features[0, pos].topk(5)\n    token = model.to_str_tokens(tokens[0, pos:pos+1])[0]\n    print(f\"Token '{token}': features {top_features.indices.tolist()}\")\n\n# 5. Reconstruct activations\nreconstructed = sae.decode(sae_features)\nreconstruction_error = (activations - reconstructed).norm()\n```\n\n### Available Pre-trained SAEs\n\n| Release | Model | Layers |\n|---------|-------|--------|\n| `gpt2-small-res-jb` | GPT-2 Small | Multiple residual streams |\n| `gemma-2b-res` | Gemma 2B | Residual streams |\n| Various on HuggingFace | Search tag `saelens` | Various |\n\n### Checklist\n- [ ] Load model with TransformerLens\n- [ ] Load matching SAE for target layer\n- [ ] Encode activations to sparse features\n- [ ] Identify top-activating features per token\n- [ ] Validate reconstruction quality\n\n## Workflow 2: Training a Custom SAE\n\n### Step-by-Step\n\n```python\nfrom sae_lens import SAE, LanguageModelSAERunnerConfig, SAETrainingRunner\n\n# 1. Configure training\ncfg = LanguageModelSAERunnerConfig(\n    # Model\n    model_name=\"gpt2-small\",\n    hook_name=\"blocks.8.hook_resid_pre\",\n    hook_layer=8,\n    d_in=768,  # Model dimension\n\n    # SAE architecture\n    architecture=\"standard\",  # or \"gated\", \"topk\"\n    d_sae=768 * 8,  # Expansion factor of 8\n    activation_fn=\"relu\",\n\n    # Training\n    lr=4e-4,\n    l1_coefficient=8e-5,  # Sparsity penalty\n    l1_warm_up_steps=1000,\n    train_batch_size_tokens=4096,\n    training_tokens=100_000_000,\n\n    # Data\n    dataset_path=\"monology\u002Fpile-uncopyrighted\",\n    context_size=128,\n\n    # Logging\n    log_to_wandb=True,\n    wandb_project=\"sae-training\",\n\n    # Checkpointing\n    checkpoint_path=\"checkpoints\",\n    n_checkpoints=5,\n)\n\n# 2. Train\ntrainer = SAETrainingRunner(cfg)\nsae = trainer.run()\n\n# 3. Evaluate\nprint(f\"L0 (avg active features): {trainer.metrics['l0']}\")\nprint(f\"CE Loss Recovered: {trainer.metrics['ce_loss_score']}\")\n```\n\n### Key Hyperparameters\n\n| Parameter | Typical Value | Effect |\n|-----------|---------------|--------|\n| `d_sae` | 4-16× d_model | More features, higher capacity |\n| `l1_coefficient` | 5e-5 to 1e-4 | Higher = sparser, less accurate |\n| `lr` | 1e-4 to 1e-3 | Standard optimizer LR |\n| `l1_warm_up_steps` | 500-2000 | Prevents early feature death |\n\n### Evaluation Metrics\n\n| Metric | Target | Meaning |\n|--------|--------|---------|\n| **L0** | 50-200 | Average active features per token |\n| **CE Loss Score** | 80-95% | Cross-entropy recovered vs original |\n| **Dead Features** | \u003C5% | Features that never activate |\n| **Explained Variance** | >90% | Reconstruction quality |\n\n### Checklist\n- [ ] Choose target layer and hook point\n- [ ] Set expansion factor (d_sae = 4-16× d_model)\n- [ ] Tune L1 coefficient for desired sparsity\n- [ ] Enable L1 warm-up to prevent dead features\n- [ ] Monitor metrics during training (W&B)\n- [ ] Validate L0 and CE loss recovery\n- [ ] Check dead feature ratio\n\n## Workflow 3: Feature Analysis and Steering\n\n### Analyzing Individual Features\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, _, _ = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# Find what activates a specific feature\nfeature_idx = 1234\ntest_texts = [\n    \"The scientist conducted an experiment\",\n    \"I love chocolate cake\",\n    \"The code compiles successfully\",\n    \"Paris is beautiful in spring\",\n]\n\nfor text in test_texts:\n    tokens = model.to_tokens(text)\n    _, cache = model.run_with_cache(tokens)\n    features = sae.encode(cache[\"resid_pre\", 8])\n    activation = features[0, :, feature_idx].max().item()\n    print(f\"{activation:.3f}: {text}\")\n```\n\n### Feature Steering\n\n```python\ndef steer_with_feature(model, sae, prompt, feature_idx, strength=5.0):\n    \"\"\"Add SAE feature direction to residual stream.\"\"\"\n    tokens = model.to_tokens(prompt)\n\n    # Get feature direction from decoder\n    feature_direction = sae.W_dec[feature_idx]  # [d_model]\n\n    def steering_hook(activation, hook):\n        # Add scaled feature direction at all positions\n        activation += strength * feature_direction\n        return activation\n\n    # Generate with steering\n    output = model.generate(\n        tokens,\n        max_new_tokens=50,\n        fwd_hooks=[(\"blocks.8.hook_resid_pre\", steering_hook)]\n    )\n    return model.to_string(output[0])\n```\n\n### Feature Attribution\n\n```python\n# Which features most affect a specific output?\ntokens = model.to_tokens(\"The capital of France is\")\n_, cache = model.run_with_cache(tokens)\n\n# Get features at final position\nfeatures = sae.encode(cache[\"resid_pre\", 8])[0, -1]  # [d_sae]\n\n# Get logit attribution per feature\n# Feature contribution = feature_activation × decoder_weight × unembedding\nW_dec = sae.W_dec  # [d_sae, d_model]\nW_U = model.W_U    # [d_model, vocab]\n\n# Contribution to \"Paris\" logit\nparis_token = model.to_single_token(\" Paris\")\nfeature_contributions = features * (W_dec @ W_U[:, paris_token])\n\ntop_features = feature_contributions.topk(10)\nprint(\"Top features for 'Paris' prediction:\")\nfor idx, val in zip(top_features.indices, top_features.values):\n    print(f\"  Feature {idx.item()}: {val.item():.3f}\")\n```\n\n## Common Issues & Solutions\n\n### Issue: High dead feature ratio\n```python\n# WRONG: No warm-up, features die early\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,\n    l1_warm_up_steps=0,  # Bad!\n)\n\n# RIGHT: Warm-up L1 penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=8e-5,\n    l1_warm_up_steps=1000,  # Gradually increase\n    use_ghost_grads=True,   # Revive dead features\n)\n```\n\n### Issue: Poor reconstruction (low CE recovery)\n```python\n# Reduce sparsity penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=5e-5,  # Lower = better reconstruction\n    d_sae=768 * 16,       # More capacity\n)\n```\n\n### Issue: Features not interpretable\n```python\n# Increase sparsity (higher L1)\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,  # Higher = sparser, more interpretable\n)\n# Or use TopK architecture\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn_kwargs={\"k\": 50},  # Exactly 50 active features\n)\n```\n\n### Issue: Memory errors during training\n```python\ncfg = LanguageModelSAERunnerConfig(\n    train_batch_size_tokens=2048,  # Reduce batch size\n    store_batch_size_prompts=4,    # Fewer prompts in buffer\n    n_batches_in_buffer=8,         # Smaller activation buffer\n)\n```\n\n## Integration with Neuronpedia\n\nBrowse pre-trained SAE features at [neuronpedia.org](https:\u002F\u002Fneuronpedia.org):\n\n```python\n# Features are indexed by SAE ID\n# Example: gpt2-small layer 8 feature 1234\n# → neuronpedia.org\u002Fgpt2-small\u002F8-res-jb\u002F1234\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `SAE` | Sparse Autoencoder model |\n| `LanguageModelSAERunnerConfig` | Training configuration |\n| `SAETrainingRunner` | Training loop manager |\n| `ActivationsStore` | Activation collection and batching |\n| `HookedSAETransformer` | TransformerLens + SAE integration |\n\n## Reference Documentation\n\nFor detailed API documentation, tutorials, and advanced usage, see the `references\u002F` folder:\n\n| File | Contents |\n|------|----------|\n| [references\u002FREADME.md](references\u002FREADME.md) | Overview and quick start guide |\n| [references\u002Fapi.md](references\u002Fapi.md) | Complete API reference for SAE, TrainingSAE, configurations |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for training, analysis, steering |\n\n## External Resources\n\n### Tutorials\n- [Basic Loading & Analysis](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Fbasic_loading_and_analysing.ipynb)\n- [Training a Sparse Autoencoder](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Ftraining_a_sparse_autoencoder.ipynb)\n- [ARENA SAE Curriculum](https:\u002F\u002Fwww.lesswrong.com\u002Fposts\u002FLnHowHgmrMbWtpkxx\u002Fintro-to-superposition-and-sparse-autoencoders-colab)\n\n### Papers\n- [Towards Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2023\u002Fmonosemantic-features) - Anthropic (2023)\n- [Scaling Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2024\u002Fscaling-monosemanticity\u002F) - Anthropic (2024)\n- [Sparse Autoencoders Find Highly Interpretable Features](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.08600) - Cunningham et al. (ICLR 2024)\n\n### Official Documentation\n- [SAELens Docs](https:\u002F\u002Fjbloomaus.github.io\u002FSAELens\u002F)\n- [Neuronpedia](https:\u002F\u002Fneuronpedia.org) - Feature browser\n\n## SAE Architectures\n\n| Architecture | Description | Use Case |\n|--------------|-------------|----------|\n| **Standard** | ReLU + L1 penalty | General purpose |\n| **Gated** | Learned gating mechanism | Better sparsity control |\n| **TopK** | Exactly K active features | Consistent sparsity |\n\n```python\n# TopK SAE (exactly 50 features active)\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn=\"topk\",\n    activation_fn_kwargs={\"k\": 50},\n)\n```\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the model, checkpoint, benchmark version and evaluation harness version.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Evaluate on a small subset to verify prompts, parsing and scoring.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Use the benchmark's official splits and metrics; check for contamination; report variance across seeds or prompts.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Scores differ from published numbers | Check prompt format, few-shot settings and harness version before concluding. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Report evaluation settings in full; never cherry-pick prompts, seeds or subsets.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `nnsight-remote-interpretability`: Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.\n- `unsloth`: Provides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, base…\n- `transformer-lens-interpretability`: Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookP…\n","# SAELens: Sparse Autoencoders for Mechanistic Interpretability\n\nSAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.\n\n**GitHub**: [jbloomAus\u002FSAELens](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens)\n\n## The Problem: Polysemanticity & Superposition\n\nIndividual neurons in neural networks are **polysemantic** - they activate in multiple, semantically distinct contexts. This happens because models use **superposition** to represent more features than they have neurons, making interpretability difficult.\n\n**SAEs solve this** by decomposing dense activations into sparse, monosemantic features - typically only a small number of features activate for any given input, and each feature corresponds to an interpretable concept.\n\n## When to Use SAELens\n\n**Use SAELens when you need to:**\n- Discover interpretable features in model activations\n- Understand what concepts a model has learned\n- Study superposition and feature geometry\n- Perform feature-based steering or ablation\n- Analyze safety-relevant features (deception, bias, harmful content)\n\n**Consider alternatives when:**\n- You need basic activation analysis → Use **TransformerLens** directly\n- You want causal intervention experiments → Use **pyvene** or **TransformerLens**\n- You need production steering → Consider direct activation engineering\n\n## Installation\n\n```bash\npip install sae-lens\n```\n\nRequirements: Python 3.10+, transformer-lens>=2.0.0\n\n## Core Concepts\n\n### What SAEs Learn\n\nSAEs are trained to reconstruct model activations through a sparse bottleneck:\n\n```\nInput Activation → Encoder → Sparse Features → Decoder → Reconstructed Activation\n    (d_model)       ↓        (d_sae >> d_model)    ↓         (d_model)\n                 sparsity                      reconstruction\n                 penalty                          loss\n```\n\n**Loss Function**: `MSE(original, reconstructed) + L1_coefficient × L1(features)`\n\n### Key Validation (Anthropic Research)\n\nIn \"Towards Monosemanticity\", human evaluators found **70% of SAE features genuinely interpretable**. Features discovered include:\n- DNA sequences, legal language, HTTP requests\n- Hebrew text, nutrition statements, code syntax\n- Sentiment, named entities, grammatical structures\n\n## Workflow 1: Loading and Analyzing Pre-trained SAEs\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\n\n# 1. Load model and pre-trained SAE\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, cfg_dict, sparsity = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# 2. Get model activations\ntokens = model.to_tokens(\"The capital of France is Paris\")\n_, cache = model.run_with_cache(tokens)\nactivations = cache[\"resid_pre\", 8]  # [batch, pos, d_model]\n\n# 3. Encode to SAE features\nsae_features = sae.encode(activations)  # [batch, pos, d_sae]\nprint(f\"Active features: {(sae_features > 0).sum()}\")\n\n# 4. Find top features for each position\nfor pos in range(tokens.shape[1]):\n    top_features = sae_features[0, pos].topk(5)\n    token = model.to_str_tokens(tokens[0, pos:pos+1])[0]\n    print(f\"Token '{token}': features {top_features.indices.tolist()}\")\n\n# 5. Reconstruct activations\nreconstructed = sae.decode(sae_features)\nreconstruction_error = (activations - reconstructed).norm()\n```\n\n### Available Pre-trained SAEs\n\n| Release | Model | Layers |\n|---------|-------|--------|\n| `gpt2-small-res-jb` | GPT-2 Small | Multiple residual streams |\n| `gemma-2b-res` | Gemma 2B | Residual streams |\n| Various on HuggingFace | Search tag `saelens` | Various |\n\n### Checklist\n- [ ] Load model with TransformerLens\n- [ ] Load matching SAE for target layer\n- [ ] Encode activations to sparse features\n- [ ] Identify top-activating features per token\n- [ ] Validate reconstruction quality\n\n## Workflow 2: Training a Custom SAE\n\n### Step-by-Step\n\n```python\nfrom sae_lens import SAE, LanguageModelSAERunnerConfig, SAETrainingRunner\n\n# 1. Configure training\ncfg = LanguageModelSAERunnerConfig(\n    # Model\n    model_name=\"gpt2-small\",\n    hook_name=\"blocks.8.hook_resid_pre\",\n    hook_layer=8,\n    d_in=768,  # Model dimension\n\n    # SAE architecture\n    architecture=\"standard\",  # or \"gated\", \"topk\"\n    d_sae=768 * 8,  # Expansion factor of 8\n    activation_fn=\"relu\",\n\n    # Training\n    lr=4e-4,\n    l1_coefficient=8e-5,  # Sparsity penalty\n    l1_warm_up_steps=1000,\n    train_batch_size_tokens=4096,\n    training_tokens=100_000_000,\n\n    # Data\n    dataset_path=\"monology\u002Fpile-uncopyrighted\",\n    context_size=128,\n\n    # Logging\n    log_to_wandb=True,\n    wandb_project=\"sae-training\",\n\n    # Checkpointing\n    checkpoint_path=\"checkpoints\",\n    n_checkpoints=5,\n)\n\n# 2. Train\ntrainer = SAETrainingRunner(cfg)\nsae = trainer.run()\n\n# 3. Evaluate\nprint(f\"L0 (avg active features): {trainer.metrics['l0']}\")\nprint(f\"CE Loss Recovered: {trainer.metrics['ce_loss_score']}\")\n```\n\n### Key Hyperparameters\n\n| Parameter | Typical Value | Effect |\n|-----------|---------------|--------|\n| `d_sae` | 4-16× d_model | More features, higher capacity |\n| `l1_coefficient` | 5e-5 to 1e-4 | Higher = sparser, less accurate |\n| `lr` | 1e-4 to 1e-3 | Standard optimizer LR |\n| `l1_warm_up_steps` | 500-2000 | Prevents early feature death |\n\n### Evaluation Metrics\n\n| Metric | Target | Meaning |\n|--------|--------|---------|\n| **L0** | 50-200 | Average active features per token |\n| **CE Loss Score** | 80-95% | Cross-entropy recovered vs original |\n| **Dead Features** | \u003C5% | Features that never activate |\n| **Explained Variance** | >90% | Reconstruction quality |\n\n### Checklist\n- [ ] Choose target layer and hook point\n- [ ] Set expansion factor (d_sae = 4-16× d_model)\n- [ ] Tune L1 coefficient for desired sparsity\n- [ ] Enable L1 warm-up to prevent dead features\n- [ ] Monitor metrics during training (W&B)\n- [ ] Validate L0 and CE loss recovery\n- [ ] Check dead feature ratio\n\n## Workflow 3: Feature Analysis and Steering\n\n### Analyzing Individual Features\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, _, _ = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# Find what activates a specific feature\nfeature_idx = 1234\ntest_texts = [\n    \"The scientist conducted an experiment\",\n    \"I love chocolate cake\",\n    \"The code compiles successfully\",\n    \"Paris is beautiful in spring\",\n]\n\nfor text in test_texts:\n    tokens = model.to_tokens(text)\n    _, cache = model.run_with_cache(tokens)\n    features = sae.encode(cache[\"resid_pre\", 8])\n    activation = features[0, :, feature_idx].max().item()\n    print(f\"{activation:.3f}: {text}\")\n```\n\n### Feature Steering\n\n```python\ndef steer_with_feature(model, sae, prompt, feature_idx, strength=5.0):\n    \"\"\"Add SAE feature direction to residual stream.\"\"\"\n    tokens = model.to_tokens(prompt)\n\n    # Get feature direction from decoder\n    feature_direction = sae.W_dec[feature_idx]  # [d_model]\n\n    def steering_hook(activation, hook):\n        # Add scaled feature direction at all positions\n        activation += strength * feature_direction\n        return activation\n\n    # Generate with steering\n    output = model.generate(\n        tokens,\n        max_new_tokens=50,\n        fwd_hooks=[(\"blocks.8.hook_resid_pre\", steering_hook)]\n    )\n    return model.to_string(output[0])\n```\n\n### Feature Attribution\n\n```python\n# Which features most affect a specific output?\ntokens = model.to_tokens(\"The capital of France is\")\n_, cache = model.run_with_cache(tokens)\n\n# Get features at final position\nfeatures = sae.encode(cache[\"resid_pre\", 8])[0, -1]  # [d_sae]\n\n# Get logit attribution per feature\n# Feature contribution = feature_activation × decoder_weight × unembedding\nW_dec = sae.W_dec  # [d_sae, d_model]\nW_U = model.W_U    # [d_model, vocab]\n\n# Contribution to \"Paris\" logit\nparis_token = model.to_single_token(\" Paris\")\nfeature_contributions = features * (W_dec @ W_U[:, paris_token])\n\ntop_features = feature_contributions.topk(10)\nprint(\"Top features for 'Paris' prediction:\")\nfor idx, val in zip(top_features.indices, top_features.values):\n    print(f\"  Feature {idx.item()}: {val.item():.3f}\")\n```\n\n## Common Issues & Solutions\n\n### Issue: High dead feature ratio\n```python\n# WRONG: No warm-up, features die early\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,\n    l1_warm_up_steps=0,  # Bad!\n)\n\n# RIGHT: Warm-up L1 penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=8e-5,\n    l1_warm_up_steps=1000,  # Gradually increase\n    use_ghost_grads=True,   # Revive dead features\n)\n```\n\n### Issue: Poor reconstruction (low CE recovery)\n```python\n# Reduce sparsity penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=5e-5,  # Lower = better reconstruction\n    d_sae=768 * 16,       # More capacity\n)\n```\n\n### Issue: Features not interpretable\n```python\n# Increase sparsity (higher L1)\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,  # Higher = sparser, more interpretable\n)\n# Or use TopK architecture\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn_kwargs={\"k\": 50},  # Exactly 50 active features\n)\n```\n\n### Issue: Memory errors during training\n```python\ncfg = LanguageModelSAERunnerConfig(\n    train_batch_size_tokens=2048,  # Reduce batch size\n    store_batch_size_prompts=4,    # Fewer prompts in buffer\n    n_batches_in_buffer=8,         # Smaller activation buffer\n)\n```\n\n## Integration with Neuronpedia\n\nBrowse pre-trained SAE features at [neuronpedia.org](https:\u002F\u002Fneuronpedia.org):\n\n```python\n# Features are indexed by SAE ID\n# Example: gpt2-small layer 8 feature 1234\n# → neuronpedia.org\u002Fgpt2-small\u002F8-res-jb\u002F1234\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `SAE` | Sparse Autoencoder model |\n| `LanguageModelSAERunnerConfig` | Training configuration |\n| `SAETrainingRunner` | Training loop manager |\n| `ActivationsStore` | Activation collection and batching |\n| `HookedSAETransformer` | TransformerLens + SAE integration |\n\n## Reference Documentation\n\nFor detailed API documentation, tutorials, and advanced usage, see the `references\u002F` folder:\n\n| File | Contents |\n|------|----------|\n| [references\u002FREADME.md](references\u002FREADME.md) | Overview and quick start guide |\n| [references\u002Fapi.md](references\u002Fapi.md) | Complete API reference for SAE, TrainingSAE, configurations |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for training, analysis, steering |\n\n## External Resources\n\n### Tutorials\n- [Basic Loading & Analysis](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Fbasic_loading_and_analysing.ipynb)\n- [Training a Sparse Autoencoder](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Ftraining_a_sparse_autoencoder.ipynb)\n- [ARENA SAE Curriculum](https:\u002F\u002Fwww.lesswrong.com\u002Fposts\u002FLnHowHgmrMbWtpkxx\u002Fintro-to-superposition-and-sparse-autoencoders-colab)\n\n### Papers\n- [Towards Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2023\u002Fmonosemantic-features) - Anthropic (2023)\n- [Scaling Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2024\u002Fscaling-monosemanticity\u002F) - Anthropic (2024)\n- [Sparse Autoencoders Find Highly Interpretable Features](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.08600) - Cunningham et al. (ICLR 2024)\n\n### Official Documentation\n- [SAELens Docs](https:\u002F\u002Fjbloomaus.github.io\u002FSAELens\u002F)\n- [Neuronpedia](https:\u002F\u002Fneuronpedia.org) - Feature browser\n\n## SAE Architectures\n\n| Architecture | Description | Use Case |\n|--------------|-------------|----------|\n| **Standard** | ReLU + L1 penalty | General purpose |\n| **Gated** | Learned gating mechanism | Better sparsity control |\n| **TopK** | Exactly K active features | Consistent sparsity |\n\n```python\n# TopK SAE (exactly 50 features active)\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn=\"topk\",\n    activation_fn_kwargs={\"k\": 50},\n)\n```\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the model, checkpoint, benchmark version and evaluation harness version.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Evaluate on a small subset to verify prompts, parsing and scoring.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Use the benchmark's official splits and metrics; check for contamination; report variance across seeds or prompts.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Scores differ from published numbers | Check prompt format, few-shot settings and harness version before concluding. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Report evaluation settings in full; never cherry-pick prompts, seeds or subsets.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `nnsight-remote-interpretability`: Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.\n- `unsloth`: Provides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, base…\n- `transformer-lens-interpretability`: Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookP…\n",{"name":5,"license":15,"metadata":45,"description":7},{"tags":46,"version":47,"category":48,"maintainer":49,"dependencies":50},"Sparse Autoencoders, SAE, Mechanistic Interpretability, Feature Discovery, Superposition","1.0.0","ml-evaluation-and-safety","Kalaris Labs","sae-lens>=6.0.0, transformer-lens>=2.0.0, torch>=2.0.0","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fsparse-autoencoder-training",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill sparse-autoencoder-training",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill sparse-autoencoder-training",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill sparse-autoencoder-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fsparse-autoencoder-training\u002FSKILL.md",true,[75,81,85],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fapi.md","REFERENCE","参考文档",6968,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fsparse-autoencoder-training\u002Freferences\u002Fapi.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002FREADME.md",2142,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fsparse-autoencoder-training\u002Freferences\u002FREADME.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Ftutorials.md",9383,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fsparse-autoencoder-training\u002Freferences\u002Ftutorials.md",[90,99,107,115,123,131],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":98},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":98},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":98},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":98},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":98},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":98},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]