Alternatives and similar repositories for nnsight

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

• decoderesearch / SAELens
  Training Sparse Autoencoders on Language Models
  ☆1,144Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆306Updated last year
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆681Updated 2 weeks ago
• saprmarks / dictionary_learning
  ☆380Updated 4 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆285Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆262Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆236Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆289Updated 2 years ago
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆848Updated 2 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆236Updated 4 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆559Updated 5 months ago
• adamkarvonen / SAEBench
  ☆140Updated last week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years 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 …
  ☆234Updated 2 weeks ago
• openai / sparse_autoencoder
  ☆557Updated last year
• callummcdougall / ARENA_3.0
  ☆872Updated last month
• jacobdunefsky / transcoder_circuits
  ☆193Updated last year
• saprmarks / feature-circuits
  ☆202Updated 2 months ago
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆331Updated 5 months ago
• neelnanda-io / Crosscoders
  ☆58Updated last year
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆389Updated last year
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆71Updated last week
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆227Updated last year
• curt-tigges / probity
  ☆20Updated 8 months ago
• ARBORproject / arborproject.github.io
  ☆83Updated 10 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆145Updated 3 weeks ago
• redwoodresearch / Easy-Transformer
  ☆135Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆225Updated 3 weeks ago
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆32Updated 2 years ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆122Updated last week