Alternatives and similar repositories for nnsight

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

• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆280Updated 8 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆609Updated last week
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆925Updated this week
• saprmarks / dictionary_learning
  ☆327Updated this week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆238Updated 10 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆212Updated 8 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆260Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆262Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆223Updated 2 weeks ago
• adamkarvonen / SAEBench
  ☆114Updated last month
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆793Updated 3 weeks ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆126Updated last year
• neelnanda-io / Crosscoders
  ☆53Updated 9 months ago
• openai / sparse_autoencoder
  ☆508Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆516Updated 2 weeks ago
• saprmarks / feature-circuits
  ☆184Updated last month
• callummcdougall / ARENA_3.0
  ☆676Updated this week
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆206Updated last week
• jacobdunefsky / transcoder_circuits
  ☆162Updated 9 months ago
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆31Updated last year
• ARBORproject / arborproject.github.io
  ☆81Updated 6 months ago
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆42Updated this week
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆368Updated 9 months ago
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆298Updated last month
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆185Updated 9 months ago
• curt-tigges / probity
  ☆15Updated 4 months ago
• collin-burns / discovering_latent_knowledge
  ☆276Updated last year
• METR / task-standard
  METR Task Standard
  ☆158Updated 6 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆88Updated this week