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).
  ☆202Updated 6 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆226Updated 8 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆207Updated 2 weeks ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆257Updated 6 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆97Updated 4 months ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆247Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆108Updated 4 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆500Updated last year
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆68Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆190Updated last year
• google-deepmind / mishax
  ☆134Updated 2 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 …
  ☆185Updated this week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆67Updated 2 months ago
• adamkarvonen / SAEBench
  ☆101Updated 3 weeks ago
• jessicarumbelow / Backwards
  ☆82Updated 11 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆126Updated 2 years ago
• collin-burns / discovering_latent_knowledge
  ☆270Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆158Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆51Updated 3 years ago
• evandez / relations
  How do transformer LMs encode relations?
  ☆48Updated last year
• HazyResearch / TART
  TART: A plug-and-play Transformer module for task-agnostic reasoning
  ☆197Updated 2 years ago
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆213Updated 7 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• jbloomAus / SAEDashboard
  ☆57Updated 2 weeks ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆70Updated last year
• kmeng01 / memit
  Mass-editing thousands of facts into a transformer memory (ICLR 2023)
  ☆500Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆67Updated 2 years ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆255Updated last year