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.
  ☆216Updated 2 weeks ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆248Updated last year
• collin-burns / discovering_latent_knowledge
  ☆283Updated last year
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆73Updated 2 years ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆236Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆559Updated 5 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆197Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆307Updated last year
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆217Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆262Updated last year
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆112Updated 10 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 8 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆132Updated 3 years ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆137Updated 10 months ago
• jessicarumbelow / Backwards
  ☆85Updated last year
• google-deepmind / mishax
  ☆150Updated 4 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆53Updated 3 years ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆84Updated last week
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆235Updated 2 weeks ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• lukasberglund / reversal_curse
  ☆301Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆198Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆76Updated 2 years ago
• redwoodresearch / Easy-Transformer
  ☆135Updated last year
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆28Updated last year
• HazyResearch / TART
  TART: A plug-and-play Transformer module for task-agnostic reasoning
  ☆202Updated 2 years ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆20Updated last year
• microsoft / mechanistic-error-probe
  A mechanistic approach for understanding and detecting factual errors of large language models.
  ☆49Updated last year