Alternatives and similar repositories for SAE-Dark-Matter

Users that are interested in SAE-Dark-Matter are comparing it to the libraries listed below

• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆162Updated 7 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 8 months ago
• IBM / sae-steering
  Code to enable layer-level steering in LLMs using sparse auto encoders
  ☆28Updated 4 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 …
  ☆235Updated last week
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆83Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆138Updated 11 months ago
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆45Updated 4 months ago
• 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
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆71Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆86Updated 3 weeks ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆26Updated last year
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆45Updated last year
• JoshEngels / SAE-Probes
  Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"
  ☆31Updated 9 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆169Updated 9 months ago
• jacobdunefsky / transcoder_circuits
  ☆195Updated 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
• saprmarks / geometry-of-truth
  ☆99Updated last year
• ahans30 / goldfish-loss
  [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs
  ☆94Updated last year
• XuchanBao / behavioral-self-awareness
  ☆34Updated 11 months ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆16Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆124Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆227Updated last month
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆64Updated last year
• bartbussmann / matryoshka_sae
  ☆57Updated last year
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆112Updated 11 months ago
• redwoodresearch / Easy-Transformer
  ☆137Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆255Updated last year
• mcleish7 / gemstone-scaling-laws
  Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)
  ☆32Updated 4 months ago
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆18Updated 9 months ago