Alternatives and similar repositories for concept-erasure:

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

• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆197Updated this week
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆230Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆235Updated 2 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆120Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆183Updated 2 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆207Updated 5 months ago
• EleutherAI / delphi
  ☆153Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆88Updated last week
• collin-burns / discovering_latent_knowledge
  ☆262Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆477Updated 9 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆84Updated 2 weeks ago
• google-deepmind / mishax
  ☆122Updated 2 weeks ago
• jacobdunefsky / transcoder_circuits
  ☆57Updated 3 months ago
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆64Updated 2 years ago
• HazyResearch / TART
  TART: A plug-and-play Transformer module for task-agnostic reasoning
  ☆195Updated last year
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆208Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆124Updated 9 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆476Updated this week
• redwoodresearch / Easy-Transformer
  ☆110Updated 6 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆186Updated 9 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆49Updated 2 years ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆54Updated 2 weeks ago
• jessicarumbelow / Backwards
  ☆78Updated 8 months ago
• anthropics / evals
  ☆255Updated 8 months ago
• davidbau / baukit
  ☆190Updated last year
• adamkarvonen / SAEBench
  ☆58Updated this week
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆217Updated 7 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆176Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆114Updated 2 years ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆217Updated last year