EleutherAI / concept-erasure

Related projects ⓘ

Alternatives and complementary repositories for concept-erasure

• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆195Updated 3 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
• EleutherAI / sae-auto-interp
  ☆99Updated this week
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆429Updated 5 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆186Updated this week
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆228Updated 8 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆186Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• saprmarks / feature-circuits
  ☆102Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆64Updated last month
• HazyResearch / TART
  TART: A plug-and-play Transformer module for task-agnostic reasoning
  ☆190Updated last year
• EleutherAI / sae
  Sparse autoencoders
  ☆333Updated 2 weeks ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆94Updated 5 months ago
• google-deepmind / mishax
  ☆99Updated 3 months ago
• collin-burns / discovering_latent_knowledge
  ☆252Updated 8 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆176Updated 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
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆161Updated 6 months ago
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆449Updated this week
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆69Updated this week
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆73Updated last month
• normster / llm_rules
  RuLES: a benchmark for evaluating rule-following in language models
  ☆210Updated last month
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆168Updated last year
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• jacobdunefsky / transcoder_circuits
  ☆43Updated 4 months ago
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆205Updated 5 months ago
• kernelmachine / cbtm
  Code repository for the c-BTM paper
  ☆105Updated last year
• sileod / tasksource
  Datasets collection and preprocessings framework for NLP extreme multitask learning
  ☆147Updated 3 months ago
• anthropics / evals
  ☆239Updated 4 months ago
• jessicarumbelow / Backwards
  ☆73Updated 4 months ago