EleutherAI / sae-auto-interp

Related projects ⓘ

Alternatives and complementary repositories for sae-auto-interp

• saprmarks / feature-circuits
  ☆102Updated last month
• jacobdunefsky / transcoder_circuits
  ☆43Updated 4 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆60Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆64Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆181Updated 11 months ago
• google-deepmind / mishax
  ☆99Updated 3 months ago
• saprmarks / dictionary_learning
  ☆141Updated 2 weeks ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆25Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆69Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆195Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆94Updated 5 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆117Updated last month
• EleutherAI / sae
  Sparse autoencoders
  ☆333Updated 2 weeks ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆186Updated last month
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆53Updated 8 months ago
• redwoodresearch / Easy-Transformer
  ☆96Updated 3 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆187Updated 3 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆30Updated last month
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆26Updated last week
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• saprmarks / geometry-of-truth
  ☆70Updated 3 months ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆208Updated 3 weeks ago
• KihoPark / linear_rep_geometry
  ☆75Updated 9 months ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆17Updated 10 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆26Updated 5 months ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆116Updated 3 weeks ago
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆61Updated 4 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆26Updated 5 months ago