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
  ☆640Updated this week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆683Updated this week
• saprmarks / dictionary_learning
  ☆348Updated last month
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆272Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆291Updated 10 months ago
• openai / sparse_autoencoder
  ☆527Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆274Updated last year
• TransformerLensOrg / TransformerLens
  A library for mechanistic interpretability of GPT-style language models
  ☆2,675Updated this week
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆819Updated last month
• ArthurConmy / Automatic-Circuit-Discovery
  ☆244Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆221Updated 10 months ago
• adamkarvonen / SAEBench
  ☆131Updated last week
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆532Updated 2 months ago
• jacobdunefsky / transcoder_circuits
  ☆175Updated 11 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆374Updated 11 months ago
• callummcdougall / ARENA_3.0
  ☆747Updated 2 weeks ago
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆202Updated 10 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆283Updated 4 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆188Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆216Updated last week
• andyzoujm / representation-engineering
  Representation Engineering: A Top-Down Approach to AI Transparency
  ☆897Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆228Updated 2 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆128Updated last year
• saprmarks / feature-circuits
  ☆190Updated this week
• neelnanda-io / Crosscoders
  ☆54Updated 11 months ago
• redwoodresearch / Easy-Transformer
  ☆126Updated last year
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆154Updated this week
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆311Updated 2 months ago
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆31Updated last year
• collin-burns / discovering_latent_knowledge
  ☆278Updated last year