Alternatives and similar repositories for concept-erasure

Users that are interested in concept-erasure are comparing it to the libraries listed below

• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆199Updated 4 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆244Updated 4 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆202Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 7 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆172Updated last week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆99Updated 2 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• collin-burns / discovering_latent_knowledge
  ☆265Updated last year
• callummcdougall / sae_visualizer
  ☆27Updated last year
• adamkarvonen / SAEBench
  ☆93Updated last month
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆67Updated 2 years ago
• google-deepmind / mishax
  ☆129Updated last month
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆490Updated 11 months ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆242Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆94Updated last month
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆94Updated 3 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆50Updated 2 years ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆73Updated 5 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆49Updated last week
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆526Updated this week
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆189Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆64Updated 3 weeks ago
• jbloomAus / SAEDashboard
  ☆38Updated last week
• saprmarks / feature-circuits
  ☆165Updated last month
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆31Updated 11 months ago
• jessicarumbelow / Backwards
  ☆81Updated 10 months ago
• KihoPark / linear_rep_geometry
  ☆92Updated 3 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆70Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆246Updated 9 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆121Updated 2 years ago