Alternatives and similar repositories for awesome-sparse-autoencoders

Users that are interested in awesome-sparse-autoencoders are comparing it to the libraries listed below

• adamkarvonen / SAEBench
  ☆142Updated last month
• jacobdunefsky / transcoder_circuits
  ☆195Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆293Updated 2 years ago
• saprmarks / feature-circuits
  ☆205Updated 3 months ago
• saprmarks / dictionary_learning
  ☆388Updated 5 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 …
  ☆238Updated this week
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆289Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆26Updated last year
• neelnanda-io / Crosscoders
  ☆58Updated last year
• bartbussmann / matryoshka_sae
  ☆57Updated last year
• AIRI-Institute / SAE-Reasoning
  ☆92Updated 10 months ago
• KihoPark / linear_rep_geometry
  ☆114Updated 11 months ago
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆229Updated last year
• OpenMOSS / Language-Model-SAEs
  Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
  ☆175Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆238Updated last year
• hannamw / EAP-IG
  ☆70Updated 6 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 9 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆207Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆265Updated last year
• saprmarks / geometry-of-truth
  ☆99Updated last year
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆25Updated 2 weeks ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆86Updated last month
• ARBORproject / arborproject.github.io
  ☆83Updated 11 months ago
• redwoodresearch / Easy-Transformer
  ☆137Updated last year
• adamkarvonen / dictionary_learning_demo
  ☆23Updated 5 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆45Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆163Updated 7 months ago
• curt-tigges / probity
  ☆20Updated 9 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆83Updated last year