Alternatives and similar repositories for devinterp

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

• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆289Updated 9 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆227Updated last month
• ArthurConmy / Automatic-Circuit-Discovery
  ☆242Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆127Updated last year
• METR / task-standard
  METR Task Standard
  ☆161Updated 7 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆221Updated 9 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆36Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆74Updated 2 years ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 9 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆267Updated last year
• amack315 / unsupervised-steering-vectors
  ☆34Updated last year
• callummcdougall / sae_visualizer
  ☆29Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆30Updated 3 months ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆78Updated 3 years ago
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆16Updated this week
• saprmarks / dictionary_learning
  ☆347Updated last month
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 5 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆98Updated this week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆672Updated last week
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆73Updated last week
• curt-tigges / probity
  ☆18Updated 5 months ago
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆14Updated last year
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆31Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆52Updated 3 years ago
• collin-burns / discovering_latent_knowledge
  ☆276Updated last year
• redwoodresearch / rust_circuit_public
  ☆64Updated 2 years ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆191Updated 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 …
  ☆213Updated last week
• redwoodresearch / Easy-Transformer
  ☆123Updated last year