Alternatives and similar repositories for SAELens

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

• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆584Updated last week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆608Updated this week
• saprmarks / dictionary_learning
  ☆314Updated last month
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆255Updated 11 months ago
• openai / sparse_autoencoder
  ☆500Updated 11 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆260Updated 6 months ago
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆764Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆259Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆206Updated 7 months ago
• TransformerLensOrg / TransformerLens
  A library for mechanistic interpretability of GPT-style language models
  ☆2,342Updated this week
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆362Updated 8 months ago
• jacobdunefsky / transcoder_circuits
  ☆140Updated 7 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆505Updated last year
• adamkarvonen / SAEBench
  ☆105Updated last month
• callummcdougall / ARENA_3.0
  ☆611Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆122Updated last year
• saprmarks / feature-circuits
  ☆182Updated 3 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 …
  ☆192Updated last week
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆170Updated 7 months ago
• andyzoujm / representation-engineering
  Representation Engineering: A Top-Down Approach to AI Transparency
  ☆848Updated 11 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆238Updated last month
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆216Updated last year
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆30Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆162Updated last year
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆285Updated 2 weeks ago
• neelnanda-io / Crosscoders
  ☆47Updated 7 months ago
• collin-burns / discovering_latent_knowledge
  ☆273Updated last year
• shehper / sparse-dictionary-learning
  An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"
  ☆46Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆112Updated 4 months ago