jacobdunefsky / transcoder_circuits

Related projects: ⓘ

• saprmarks / feature-circuits
  ☆75Updated this week
• EleutherAI / sae-auto-interp
  ☆54Updated last week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆18Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆99Updated 10 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆25Updated 3 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆133Updated last month
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆57Updated last week
• saprmarks / dictionary_learning
  ☆110Updated 3 weeks ago
• KihoPark / linear_rep_geometry
  ☆68Updated 7 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆48Updated 2 years ago
• callummcdougall / sae_visualizer
  ☆24Updated 5 months ago
• redwoodresearch / Easy-Transformer
  ☆91Updated last month
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆14Updated 8 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆174Updated 4 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆51Updated 7 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆162Updated 10 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆54Updated 10 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆175Updated 2 months ago
• berlino / seq_icl
  ☆48Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆83Updated 3 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆22Updated 3 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆47Updated 9 months ago
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆50Updated last year
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆165Updated last year
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆66Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆52Updated last month
• thestephencasper / everything-you-need
  we got you bro
  ☆32Updated last month
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆76Updated 3 weeks ago
• saprmarks / geometry-of-truth
  ☆64Updated last month
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆26Updated last month