EleutherAI / concept-erasure

Related projects ⓘ

Alternatives and complementary repositories for concept-erasure

• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆186Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆158Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆65Updated this week
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆229Updated 9 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆200Updated 4 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• EleutherAI / sae-auto-interp
  ☆109Updated this week
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆432Updated 5 months ago
• collin-burns / discovering_latent_knowledge
  ☆253Updated 8 months ago
• EleutherAI / sae
  Sparse autoencoders
  ☆345Updated this week
• google-deepmind / mishax
  ☆101Updated 3 months ago
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• saprmarks / feature-circuits
  ☆106Updated last month
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆125Updated last month
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆180Updated 5 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆84Updated this week
• jacobdunefsky / transcoder_circuits
  ☆44Updated this week
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆205Updated last week
• KihoPark / linear_rep_geometry
  ☆76Updated 9 months ago
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆481Updated this week
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆61Updated last year
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆163Updated 6 months ago
• normster / llm_rules
  RuLES: a benchmark for evaluating rule-following in language models
  ☆211Updated last month
• jessicarumbelow / Backwards
  ☆74Updated 4 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆107Updated last week
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆98Updated 6 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆154Updated last month
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆49Updated 2 years ago
• kernelmachine / cbtm
  Code repository for the c-BTM paper
  ☆105Updated last year