[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KQCVKY34C90GZPMC40RAGT":3,"skill-same:01M6KQCVKY34C90GZPMC40RAGT":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":13,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6KQCVKY34C90GZPMC40RAGT","transformer-lens-interpretability",null,"Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.","endman100\u002Fskill-router-nexus","endman100","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F31997019?v=4","01M6KPDX17BYDWW4RRB0TNGGMX","01M6KPDX64Y2QBEWVFG5W5PWPF",0,"MIT","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FAI-Research\u002Ftransformer-lens\u002Ftransformer-lens\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"transformer lens interpretability","transformer lens","Interpretability","Transformer","lens","when","experiments","reverse","inspect","circuit","Activation Patching","circuit analysis","attention","caching","algorithms","patterns","activation","model","patching","analysis","reverse-engineering","2026-11-10 10:12:30",false,"---\nname: transformer-lens-interpretability\ndescription: Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Mechanistic Interpretability, TransformerLens, Activation Patching, Circuit Analysis]\ndependencies: [transformer-lens>=2.0.0, torch>=2.0.0]\n---\n\n# TransformerLens: Mechanistic Interpretability for Transformers\n\nTransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.\n\n**GitHub**: [TransformerLensOrg\u002FTransformerLens](https:\u002F\u002Fgithub.com\u002FTransformerLensOrg\u002FTransformerLens) (2,900+ stars)\n\n## When to Use TransformerLens\n\n**Use TransformerLens when you need to:**\n- Reverse-engineer algorithms learned during training\n- Perform activation patching \u002F causal tracing experiments\n- Study attention patterns and information flow\n- Analyze circuits (e.g., induction heads, IOI circuit)\n- Cache and inspect intermediate activations\n- Apply direct logit attribution\n\n**Consider alternatives when:**\n- You need to work with non-transformer architectures → Use **nnsight** or **pyvene**\n- You want to train\u002Fanalyze Sparse Autoencoders → Use **SAELens**\n- You need remote execution on massive models → Use **nnsight** with NDIF\n- You want higher-level causal intervention abstractions → Use **pyvene**\n\n## Installation\n\n```bash\npip install transformer-lens\n```\n\nFor development version:\n```bash\npip install git+https:\u002F\u002Fgithub.com\u002FTransformerLensOrg\u002FTransformerLens\n```\n\n## Core Concepts\n\n### HookedTransformer\n\nThe main class that wraps transformer models with HookPoints on every activation:\n\n```python\nfrom transformer_lens import HookedTransformer\n\n# Load a model\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# For gated models (LLaMA, Mistral)\nimport os\nos.environ[\"HF_TOKEN\"] = \"your_token\"\nmodel = HookedTransformer.from_pretrained(\"meta-llama\u002FLlama-2-7b-hf\")\n```\n\n### Supported Models (50+)\n\n| Family | Models |\n|--------|--------|\n| GPT-2 | gpt2, gpt2-medium, gpt2-large, gpt2-xl |\n| LLaMA | llama-7b, llama-13b, llama-2-7b, llama-2-13b |\n| EleutherAI | pythia-70m to pythia-12b, gpt-neo, gpt-j-6b |\n| Mistral | mistral-7b, mixtral-8x7b |\n| Others | phi, qwen, opt, gemma |\n\n### Activation Caching\n\nRun the model and cache all intermediate activations:\n\n```python\n# Get all activations\ntokens = model.to_tokens(\"The Eiffel Tower is in\")\nlogits, cache = model.run_with_cache(tokens)\n\n# Access specific activations\nresidual = cache[\"resid_post\", 5]  # Layer 5 residual stream\nattn_pattern = cache[\"pattern\", 3]  # Layer 3 attention pattern\nmlp_out = cache[\"mlp_out\", 7]  # Layer 7 MLP output\n\n# Filter which activations to cache (saves memory)\nlogits, cache = model.run_with_cache(\n    tokens,\n    names_filter=lambda name: \"resid_post\" in name\n)\n```\n\n### ActivationCache Keys\n\n| Key Pattern | Shape | Description |\n|-------------|-------|-------------|\n| `resid_pre, layer` | [batch, pos, d_model] | Residual before attention |\n| `resid_mid, layer` | [batch, pos, d_model] | Residual after attention |\n| `resid_post, layer` | [batch, pos, d_model] | Residual after MLP |\n| `attn_out, layer` | [batch, pos, d_model] | Attention output |\n| `mlp_out, layer` | [batch, pos, d_model] | MLP output |\n| `pattern, layer` | [batch, head, q_pos, k_pos] | Attention pattern (post-softmax) |\n| `q, layer` | [batch, pos, head, d_head] | Query vectors |\n| `k, layer` | [batch, pos, head, d_head] | Key vectors |\n| `v, layer` | [batch, pos, head, d_head] | Value vectors |\n\n## Workflow 1: Activation Patching (Causal Tracing)\n\nIdentify which activations causally affect model output by patching clean activations into corrupted runs.\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer, patching\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# 1. Define clean and corrupted prompts\nclean_prompt = \"The Eiffel Tower is in the city of\"\ncorrupted_prompt = \"The Colosseum is in the city of\"\n\nclean_tokens = model.to_tokens(clean_prompt)\ncorrupted_tokens = model.to_tokens(corrupted_prompt)\n\n# 2. Get clean activations\n_, clean_cache = model.run_with_cache(clean_tokens)\n\n# 3. Define metric (e.g., logit difference)\nparis_token = model.to_single_token(\" Paris\")\nrome_token = model.to_single_token(\" Rome\")\n\ndef metric(logits):\n    return logits[0, -1, paris_token] - logits[0, -1, rome_token]\n\n# 4. Patch each position and layer\nresults = torch.zeros(model.cfg.n_layers, clean_tokens.shape[1])\n\nfor layer in range(model.cfg.n_layers):\n    for pos in range(clean_tokens.shape[1]):\n        def patch_hook(activation, hook):\n            activation[0, pos] = clean_cache[hook.name][0, pos]\n            return activation\n\n        patched_logits = model.run_with_hooks(\n            corrupted_tokens,\n            fwd_hooks=[(f\"blocks.{layer}.hook_resid_post\", patch_hook)]\n        )\n        results[layer, pos] = metric(patched_logits)\n\n# 5. Visualize results (layer x position heatmap)\n```\n\n### Checklist\n- [ ] Define clean and corrupted inputs that differ minimally\n- [ ] Choose metric that captures behavior difference\n- [ ] Cache clean activations\n- [ ] Systematically patch each (layer, position) combination\n- [ ] Visualize results as heatmap\n- [ ] Identify causal hotspots\n\n## Workflow 2: Circuit Analysis (Indirect Object Identification)\n\nReplicate the IOI circuit discovery from \"Interpretability in the Wild\".\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# IOI task: \"When John and Mary went to the store, Mary gave a bottle to\"\n# Model should predict \"John\" (indirect object)\n\nprompt = \"When John and Mary went to the store, Mary gave a bottle to\"\ntokens = model.to_tokens(prompt)\n\n# 1. Get baseline logits\nlogits, cache = model.run_with_cache(tokens)\n\njohn_token = model.to_single_token(\" John\")\nmary_token = model.to_single_token(\" Mary\")\n\n# 2. Compute logit difference (IO - S)\nlogit_diff = logits[0, -1, john_token] - logits[0, -1, mary_token]\nprint(f\"Logit difference: {logit_diff.item():.3f}\")\n\n# 3. Direct logit attribution by head\ndef get_head_contribution(layer, head):\n    # Project head output to logits\n    head_out = cache[\"z\", layer][0, :, head, :]  # [pos, d_head]\n    W_O = model.W_O[layer, head]  # [d_head, d_model]\n    W_U = model.W_U  # [d_model, vocab]\n\n    # Head contribution to logits at final position\n    contribution = head_out[-1] @ W_O @ W_U\n    return contribution[john_token] - contribution[mary_token]\n\n# 4. Map all heads\nhead_contributions = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)\nfor layer in range(model.cfg.n_layers):\n    for head in range(model.cfg.n_heads):\n        head_contributions[layer, head] = get_head_contribution(layer, head)\n\n# 5. Identify top contributing heads (name movers, backup name movers)\n```\n\n### Checklist\n- [ ] Set up task with clear IO\u002FS tokens\n- [ ] Compute baseline logit difference\n- [ ] Decompose by attention head contributions\n- [ ] Identify key circuit components (name movers, S-inhibition, induction)\n- [ ] Validate with ablation experiments\n\n## Workflow 3: Induction Head Detection\n\nFind induction heads that implement [A][B]...[A] → [B] pattern.\n\n```python\nfrom transformer_lens import HookedTransformer\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# Create repeated sequence: [A][B][A] should predict [B]\nrepeated_tokens = torch.tensor([[1000, 2000, 1000]])  # Arbitrary tokens\n\n_, cache = model.run_with_cache(repeated_tokens)\n\n# Induction heads attend from final [A] back to first [B]\n# Check attention from position 2 to position 1\ninduction_scores = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)\n\nfor layer in range(model.cfg.n_layers):\n    pattern = cache[\"pattern\", layer][0]  # [head, q_pos, k_pos]\n    # Attention from pos 2 to pos 1\n    induction_scores[layer] = pattern[:, 2, 1]\n\n# Heads with high scores are induction heads\ntop_heads = torch.topk(induction_scores.flatten(), k=5)\n```\n\n## Common Issues & Solutions\n\n### Issue: Hooks persist after debugging\n```python\n# WRONG: Old hooks remain active\nmodel.run_with_hooks(tokens, fwd_hooks=[...])  # Debug, add new hooks\nmodel.run_with_hooks(tokens, fwd_hooks=[...])  # Old hooks still there!\n\n# RIGHT: Always reset hooks\nmodel.reset_hooks()\nmodel.run_with_hooks(tokens, fwd_hooks=[...])\n```\n\n### Issue: Tokenization gotchas\n```python\n# WRONG: Assuming consistent tokenization\nmodel.to_tokens(\"Tim\")  # Single token\nmodel.to_tokens(\"Neel\")  # Becomes \"Ne\" + \"el\" (two tokens!)\n\n# RIGHT: Check tokenization explicitly\ntokens = model.to_tokens(\"Neel\", prepend_bos=False)\nprint(model.to_str_tokens(tokens))  # ['Ne', 'el']\n```\n\n### Issue: LayerNorm ignored in analysis\n```python\n# WRONG: Ignoring LayerNorm\npre_activation = residual @ model.W_in[layer]\n\n# RIGHT: Include LayerNorm\nln_scale = model.blocks[layer].ln2.w\nln_out = model.blocks[layer].ln2(residual)\npre_activation = ln_out @ model.W_in[layer]\n```\n\n### Issue: Memory explosion with large models\n```python\n# Use selective caching\nlogits, cache = model.run_with_cache(\n    tokens,\n    names_filter=lambda n: \"resid_post\" in n or \"pattern\" in n,\n    device=\"cpu\"  # Cache on CPU\n)\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `HookedTransformer` | Main model wrapper with hooks |\n| `ActivationCache` | Dictionary-like cache of activations |\n| `HookedTransformerConfig` | Model configuration |\n| `FactoredMatrix` | Efficient factored matrix operations |\n\n## Integration with SAELens\n\nTransformerLens integrates with SAELens for Sparse Autoencoder analysis:\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\nsae = SAE.from_pretrained(\"gpt2-small-res-jb\", \"blocks.8.hook_resid_pre\")\n\n# Run with SAE\ntokens = model.to_tokens(\"Hello world\")\n_, cache = model.run_with_cache(tokens)\nsae_acts = sae.encode(cache[\"resid_pre\", 8])\n```\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 HookedTransformer, ActivationCache, HookPoints |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for activation patching, circuit analysis, logit lens |\n\n## External Resources\n\n### Tutorials\n- [Main Demo Notebook](https:\u002F\u002Ftransformerlensorg.github.io\u002FTransformerLens\u002Fgenerated\u002Fdemos\u002FMain_Demo.html)\n- [Activation Patching Demo](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002FTransformerLensOrg\u002FTransformerLens\u002Fblob\u002Fmain\u002Fdemos\u002FActivation_Patching_in_TL_Demo.ipynb)\n- [ARENA Mech Interp Course](https:\u002F\u002Farena-foundation.github.io\u002FARENA\u002F) - 200+ hours of tutorials\n\n### Papers\n- [A Mathematical Framework for Transformer Circuits](https:\u002F\u002Ftransformer-circuits.pub\u002F2021\u002Fframework\u002Findex.html)\n- [In-context Learning and Induction Heads](https:\u002F\u002Ftransformer-circuits.pub\u002F2022\u002Fin-context-learning-and-induction-heads\u002Findex.html)\n- [Interpretability in the Wild (IOI)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.00593)\n\n### Official Documentation\n- [Official Docs](https:\u002F\u002Ftransformerlensorg.github.io\u002FTransformerLens\u002F)\n- [Model Properties Table](https:\u002F\u002Ftransformerlensorg.github.io\u002FTransformerLens\u002Fgenerated\u002Fmodel_properties_table.html)\n- [Neel Nanda's Glossary](https:\u002F\u002Fwww.neelnanda.io\u002Fmechanistic-interpretability\u002Fglossary)\n\n## Version Notes\n\n- **v2.0**: Removed HookedSAE (moved to SAELens)\n- **v3.0 (alpha)**: TransformerBridge for loading any nn.Module\n","# TransformerLens: Mechanistic Interpretability for Transformers\n\nTransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.\n\n**GitHub**: [TransformerLensOrg\u002FTransformerLens](https:\u002F\u002Fgithub.com\u002FTransformerLensOrg\u002FTransformerLens) (2,900+ stars)\n\n## When to Use TransformerLens\n\n**Use TransformerLens when you need to:**\n- Reverse-engineer algorithms learned during training\n- Perform activation patching \u002F causal tracing experiments\n- Study attention patterns and information flow\n- Analyze circuits (e.g., induction heads, IOI circuit)\n- Cache and inspect intermediate activations\n- Apply direct logit attribution\n\n**Consider alternatives when:**\n- You need to work with non-transformer architectures → Use **nnsight** or **pyvene**\n- You want to train\u002Fanalyze Sparse Autoencoders → Use **SAELens**\n- You need remote execution on massive models → Use **nnsight** with NDIF\n- You want higher-level causal intervention abstractions → Use **pyvene**\n\n## Installation\n\n```bash\npip install transformer-lens\n```\n\nFor development version:\n```bash\npip install git+https:\u002F\u002Fgithub.com\u002FTransformerLensOrg\u002FTransformerLens\n```\n\n## Core Concepts\n\n### HookedTransformer\n\nThe main class that wraps transformer models with HookPoints on every activation:\n\n```python\nfrom transformer_lens import HookedTransformer\n\n# Load a model\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# For gated models (LLaMA, Mistral)\nimport os\nos.environ[\"HF_TOKEN\"] = \"your_token\"\nmodel = HookedTransformer.from_pretrained(\"meta-llama\u002FLlama-2-7b-hf\")\n```\n\n### Supported Models (50+)\n\n| Family | Models |\n|--------|--------|\n| GPT-2 | gpt2, gpt2-medium, gpt2-large, gpt2-xl |\n| LLaMA | llama-7b, llama-13b, llama-2-7b, llama-2-13b |\n| EleutherAI | pythia-70m to pythia-12b, gpt-neo, gpt-j-6b |\n| Mistral | mistral-7b, mixtral-8x7b |\n| Others | phi, qwen, opt, gemma |\n\n### Activation Caching\n\nRun the model and cache all intermediate activations:\n\n```python\n# Get all activations\ntokens = model.to_tokens(\"The Eiffel Tower is in\")\nlogits, cache = model.run_with_cache(tokens)\n\n# Access specific activations\nresidual = cache[\"resid_post\", 5]  # Layer 5 residual stream\nattn_pattern = cache[\"pattern\", 3]  # Layer 3 attention pattern\nmlp_out = cache[\"mlp_out\", 7]  # Layer 7 MLP output\n\n# Filter which activations to cache (saves memory)\nlogits, cache = model.run_with_cache(\n    tokens,\n    names_filter=lambda name: \"resid_post\" in name\n)\n```\n\n### ActivationCache Keys\n\n| Key Pattern | Shape | Description |\n|-------------|-------|-------------|\n| `resid_pre, layer` | [batch, pos, d_model] | Residual before attention |\n| `resid_mid, layer` | [batch, pos, d_model] | Residual after attention |\n| `resid_post, layer` | [batch, pos, d_model] | Residual after MLP |\n| `attn_out, layer` | [batch, pos, d_model] | Attention output |\n| `mlp_out, layer` | [batch, pos, d_model] | MLP output |\n| `pattern, layer` | [batch, head, q_pos, k_pos] | Attention pattern (post-softmax) |\n| `q, layer` | [batch, pos, head, d_head] | Query vectors |\n| `k, layer` | [batch, pos, head, d_head] | Key vectors |\n| `v, layer` | [batch, pos, head, d_head] | Value vectors |\n\n## Workflow 1: Activation Patching (Causal Tracing)\n\nIdentify which activations causally affect model output by patching clean activations into corrupted runs.\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer, patching\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# 1. Define clean and corrupted prompts\nclean_prompt = \"The Eiffel Tower is in the city of\"\ncorrupted_prompt = \"The Colosseum is in the city of\"\n\nclean_tokens = model.to_tokens(clean_prompt)\ncorrupted_tokens = model.to_tokens(corrupted_prompt)\n\n# 2. Get clean activations\n_, clean_cache = model.run_with_cache(clean_tokens)\n\n# 3. Define metric (e.g., logit difference)\nparis_token = model.to_single_token(\" Paris\")\nrome_token = model.to_single_token(\" Rome\")\n\ndef metric(logits):\n    return logits[0, -1, paris_token] - logits[0, -1, rome_token]\n\n# 4. Patch each position and layer\nresults = torch.zeros(model.cfg.n_layers, clean_tokens.shape[1])\n\nfor layer in range(model.cfg.n_layers):\n    for pos in range(clean_tokens.shape[1]):\n        def patch_hook(activation, hook):\n            activation[0, pos] = clean_cache[hook.name][0, pos]\n            return activation\n\n        patched_logits = model.run_with_hooks(\n            corrupted_tokens,\n            fwd_hooks=[(f\"blocks.{layer}.hook_resid_post\", patch_hook)]\n        )\n        results[layer, pos] = metric(patched_logits)\n\n# 5. Visualize results (layer x position heatmap)\n```\n\n### Checklist\n- [ ] Define clean and corrupted inputs that differ minimally\n- [ ] Choose metric that captures behavior difference\n- [ ] Cache clean activations\n- [ ] Systematically patch each (layer, position) combination\n- [ ] Visualize results as heatmap\n- [ ] Identify causal hotspots\n\n## Workflow 2: Circuit Analysis (Indirect Object Identification)\n\nReplicate the IOI circuit discovery from \"Interpretability in the Wild\".\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# IOI task: \"When John and Mary went to the store, Mary gave a bottle to\"\n# Model should predict \"John\" (indirect object)\n\nprompt = \"When John and Mary went to the store, Mary gave a bottle to\"\ntokens = model.to_tokens(prompt)\n\n# 1. Get baseline logits\nlogits, cache = model.run_with_cache(tokens)\n\njohn_token = model.to_single_token(\" John\")\nmary_token = model.to_single_token(\" Mary\")\n\n# 2. Compute logit difference (IO - S)\nlogit_diff = logits[0, -1, john_token] - logits[0, -1, mary_token]\nprint(f\"Logit difference: {logit_diff.item():.3f}\")\n\n# 3. Direct logit attribution by head\ndef get_head_contribution(layer, head):\n    # Project head output to logits\n    head_out = cache[\"z\", layer][0, :, head, :]  # [pos, d_head]\n    W_O = model.W_O[layer, head]  # [d_head, d_model]\n    W_U = model.W_U  # [d_model, vocab]\n\n    # Head contribution to logits at final position\n    contribution = head_out[-1] @ W_O @ W_U\n    return contribution[john_token] - contribution[mary_token]\n\n# 4. Map all heads\nhead_contributions = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)\nfor layer in range(model.cfg.n_layers):\n    for head in range(model.cfg.n_heads):\n        head_contributions[layer, head] = get_head_contribution(layer, head)\n\n# 5. Identify top contributing heads (name movers, backup name movers)\n```\n\n### Checklist\n- [ ] Set up task with clear IO\u002FS tokens\n- [ ] Compute baseline logit difference\n- [ ] Decompose by attention head contributions\n- [ ] Identify key circuit components (name movers, S-inhibition, induction)\n- [ ] Validate with ablation experiments\n\n## Workflow 3: Induction Head Detection\n\nFind induction heads that implement [A][B]...[A] → [B] pattern.\n\n```python\nfrom transformer_lens import HookedTransformer\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\n\n# Create repeated sequence: [A][B][A] should predict [B]\nrepeated_tokens = torch.tensor([[1000, 2000, 1000]])  # Arbitrary tokens\n\n_, cache = model.run_with_cache(repeated_tokens)\n\n# Induction heads attend from final [A] back to first [B]\n# Check attention from position 2 to position 1\ninduction_scores = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)\n\nfor layer in range(model.cfg.n_layers):\n    pattern = cache[\"pattern\", layer][0]  # [head, q_pos, k_pos]\n    # Attention from pos 2 to pos 1\n    induction_scores[layer] = pattern[:, 2, 1]\n\n# Heads with high scores are induction heads\ntop_heads = torch.topk(induction_scores.flatten(), k=5)\n```\n\n## Common Issues & Solutions\n\n### Issue: Hooks persist after debugging\n```python\n# WRONG: Old hooks remain active\nmodel.run_with_hooks(tokens, fwd_hooks=[...])  # Debug, add new hooks\nmodel.run_with_hooks(tokens, fwd_hooks=[...])  # Old hooks still there!\n\n# RIGHT: Always reset hooks\nmodel.reset_hooks()\nmodel.run_with_hooks(tokens, fwd_hooks=[...])\n```\n\n### Issue: Tokenization gotchas\n```python\n# WRONG: Assuming consistent tokenization\nmodel.to_tokens(\"Tim\")  # Single token\nmodel.to_tokens(\"Neel\")  # Becomes \"Ne\" + \"el\" (two tokens!)\n\n# RIGHT: Check tokenization explicitly\ntokens = model.to_tokens(\"Neel\", prepend_bos=False)\nprint(model.to_str_tokens(tokens))  # ['Ne', 'el']\n```\n\n### Issue: LayerNorm ignored in analysis\n```python\n# WRONG: Ignoring LayerNorm\npre_activation = residual @ model.W_in[layer]\n\n# RIGHT: Include LayerNorm\nln_scale = model.blocks[layer].ln2.w\nln_out = model.blocks[layer].ln2(residual)\npre_activation = ln_out @ model.W_in[layer]\n```\n\n### Issue: Memory explosion with large models\n```python\n# Use selective caching\nlogits, cache = model.run_with_cache(\n    tokens,\n    names_filter=lambda n: \"resid_post\" in n or \"pattern\" in n,\n    device=\"cpu\"  # Cache on CPU\n)\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `HookedTransformer` | Main model wrapper with hooks |\n| `ActivationCache` | Dictionary-like cache of activations |\n| `HookedTransformerConfig` | Model configuration |\n| `FactoredMatrix` | Efficient factored matrix operations |\n\n## Integration with SAELens\n\nTransformerLens integrates with SAELens for Sparse Autoencoder analysis:\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\")\nsae = SAE.from_pretrained(\"gpt2-small-res-jb\", \"blocks.8.hook_resid_pre\")\n\n# Run with SAE\ntokens = model.to_tokens(\"Hello world\")\n_, cache = model.run_with_cache(tokens)\nsae_acts = sae.encode(cache[\"resid_pre\", 8])\n```\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 HookedTransformer, ActivationCache, HookPoints |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for activation patching, circuit analysis, logit lens |\n\n## External Resources\n\n### Tutorials\n- [Main Demo Notebook](https:\u002F\u002Ftransformerlensorg.github.io\u002FTransformerLens\u002Fgenerated\u002Fdemos\u002FMain_Demo.html)\n- [Activation Patching Demo](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002FTransformerLensOrg\u002FTransformerLens\u002Fblob\u002Fmain\u002Fdemos\u002FActivation_Patching_in_TL_Demo.ipynb)\n- [ARENA Mech Interp Course](https:\u002F\u002Farena-foundation.github.io\u002FARENA\u002F) - 200+ hours of tutorials\n\n### Papers\n- [A Mathematical Framework for Transformer Circuits](https:\u002F\u002Ftransformer-circuits.pub\u002F2021\u002Fframework\u002Findex.html)\n- [In-context Learning and Induction Heads](https:\u002F\u002Ftransformer-circuits.pub\u002F2022\u002Fin-context-learning-and-induction-heads\u002Findex.html)\n- [Interpretability in the Wild (IOI)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.00593)\n\n### Official Documentation\n- [Official Docs](https:\u002F\u002Ftransformerlensorg.github.io\u002FTransformerLens\u002F)\n- [Model Properties Table](https:\u002F\u002Ftransformerlensorg.github.io\u002FTransformerLens\u002Fgenerated\u002Fmodel_properties_table.html)\n- [Neel Nanda's Glossary](https:\u002F\u002Fwww.neelnanda.io\u002Fmechanistic-interpretability\u002Fglossary)\n\n## Version Notes\n\n- **v2.0**: Removed HookedSAE (moved to SAELens)\n- **v3.0 (alpha)**: TransformerBridge for loading any nn.Module\n",{"name":5,"tags":49,"author":53,"license":14,"version":54,"description":7,"dependencies":55},[50,51,33,52],"Mechanistic Interpretability","TransformerLens","Circuit Analysis","Orchestra Research","1.0.0",[56,57],"transformer-lens>=2.0.0","torch>=2.0.0","main","f19b254e8975d0bfddb394686706106930d7964d","AI-Research\u002Ftransformer-lens\u002Ftransformer-lens","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus","https:\u002F\u002Fgithub.com\u002Fendman100","2026-11-12 18:13:37",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add endman100\u002Fskill-router-nexus --skill transformer-lens-interpretability",{"tool":70,"command":71},"bunx","bunx skills add endman100\u002Fskill-router-nexus --skill transformer-lens-interpretability",{"tool":73,"command":74},"pnpm","pnpm dlx skills add endman100\u002Fskill-router-nexus --skill transformer-lens-interpretability","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FAI-Research\u002Ftransformer-lens\u002Ftransformer-lens\u002FSKILL.md",true,[78,84,88],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fapi.md","REFERENCE","参考文档",8349,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FAI-Research\u002Ftransformer-lens\u002Ftransformer-lens\u002Freferences\u002Fapi.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002FREADME.md",1643,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FAI-Research\u002Ftransformer-lens\u002Ftransformer-lens\u002Freferences\u002FREADME.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Ftutorials.md",10142,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FAI-Research\u002Ftransformer-lens\u002Ftransformer-lens\u002Freferences\u002Ftutorials.md",[93,117,152,173,182,206],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":105,"publishedAt":44},"01M6MPCT5BXVER8HQZTW3QE9AS","create-master","基于佛教经典文献，生成特定高僧大德的 AI 教学角色","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FMetaphysics-and-Spirituality\u002FMaster-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FMetaphysics-and-Spirituality\u002FMaster-skill\u002FSKILL.md",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[106,107,108,109,110,111,112,113,114,115,116],"create master","master","create","生成","true","webfetch","edit","write","read","grep","Bash",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":133,"publishedAt":44},"01M6M43AKE95Y64E1JRXEF5QQ3","writing-dna-skill","从至少 20 篇完整文章中蒸馏可复用的写作 DNA，分析语言、文章结构、选题逻辑、素材策略、认知框架和视觉风格，并生成 Writing-DNA.md；按该 DNA 写作时会读取全部蒸馏产物和 5 篇相关原文。用于中英文作者、账号、品牌或出版物的风格分析与一致性写作。 Distill reusable Writing DNA from at least 20 complete articles for Chinese or English authors, publications, brands, and accounts; use for language, structure, topic logic, source strategy, cognitive-frame, and visual-style analysis.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fwriting-dna-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fwriting-dna-skill\u002FSKILL.md",[124,127,130],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":128,"categoryName":129,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":131,"categoryName":132,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000036","内容创作者",[134,135,136,137,138,139,140,141,142,143,144,145,146,109,42,147,148,149,150,151],"writing dna skill","DNA","writing","strategy","english","logic","visual","structure","chinese","reusable","use","style","distill","frame","source","for","at","complete",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":156,"sourceHtmlUrl":157,"categories":158,"keywords":161,"publishedAt":44},"01M6M428TTCGQ4ME3KY99VN037","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fstop-slop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fstop-slop\u002FSKILL.md",[159,160],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":131,"categoryName":132,"taxonomyType":103,"taxonomyTypeDesc":104},[162,163,164,165,28,166,167,38,168,144,169,170,171,149,172,136],"slop","stop slop","stop","drafting","drafts","https","prose","remove","editing","text","content",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":177,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":44},"01M6M41X0B7EBX42TK435DMGGR","shuorenhua","检查和清理中英文文本里的 AI 套路，适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求；按场景控制力度，同时保留事实、术语、语域和责任主体。","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fshuorenhua\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fshuorenhua\u002FSKILL.md",[],[175,181],"文本",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":186,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":44},"01M6M3ZD12WBEW5KXKDM4N6DFG","naming","Name products, SaaS, brands, open source projects, bots, and apps. Use when the user needs to name something, find a brand name, or pick a product name. Metaphor-driven process that produces memorable, meaningful names and avoids AI slop.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fnaming-main\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fnaming-main\u002FSKILL.md",[],[184,190,191,192,193,194,144,195,114,148,196,197,198,199,116,200,201,202,203,28,204,205,162],"repo","websearch","product name","apps","bots","view","brand","pick","gh","projects","open","saas","open source","product","describe","ai slop",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":210,"sourceHtmlUrl":211,"categories":212,"keywords":214,"publishedAt":44},"01M6M3YVXAFAAWJ7F6JMPFREYE","humanizer-zh","去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。\n基于维基百科的\"AI 写作特征\"综合指南。检测并修复以下模式：夸大的象征意义、\n宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、\nAI 词汇、否定式排比、过多的连接性短语。","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fhumanizer-zh\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fhumanizer-zh\u002FSKILL.md",[213],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},[215,216,217,114,113,112,136,109,181,218,162,164],"humanizer","zh","humanizer zh","翻译"]