Alternatives and similar repositories for HypotheSAEs

Users that are interested in HypotheSAEs are comparing it to the libraries listed below

• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆241Updated last week
• Weixin-Liang / Mapping-the-Increasing-Use-of-LLMs-in-Scientific-Papers
  ☆64Updated last month
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆112Updated 11 months ago
• PAIR-code / interpretability
  PAIR.withgoogle.com and friend's work on interpretability methods
  ☆220Updated this week
• sambowyer / bayes_evals
  A lightweight library for Bayesian analysis of LLM evals (ICML 2025 Spotlight Position Paper)
  ☆21Updated 8 months ago
• dannyallover / llm_forecasting
  Forecasting with LLMs
  ☆55Updated last year
• allenai / discoverybench
  Discovering Data-driven Hypotheses in the Wild
  ☆128Updated 7 months ago
• jbloomAus / SAEDashboard
  ☆88Updated last month
• adamkarvonen / SAEBench
  ☆143Updated last month
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆33Updated 7 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆227Updated last month
• goodfire-ai / scribe
  ☆70Updated 3 weeks ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆290Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated 3 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆140Updated 11 months ago
• ndif-team / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆87Updated last week
• HannahKirk / prism-alignment
  The Prism Alignment Project
  ☆88Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆238Updated last year
• bartbussmann / BatchTopK
  Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
  ☆60Updated 6 months ago
• tatsu-lab / opinions_qa
  ☆117Updated last year
• mega002 / llm-interp-tau
  Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
  ☆297Updated 3 weeks ago
• causalNLP / cladder
  We develop benchmarks and analysis tools to evaluate the causal reasoning abilities of LLMs.
  ☆137Updated last year
• ajyl / mech_int_othelloGPT
  ☆10Updated last year
• jmerullo / lm_vector_arithmetic
  ☆36Updated 2 years ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆170Updated 9 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆267Updated last year
• causalNLP / corr2cause
  Data and code for the Corr2Cause paper (ICLR 2024)
  ☆114Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• ARBORproject / arborproject.github.io
  ☆83Updated 11 months ago