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
  ☆260Updated 6 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆122Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 6 months ago
• 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
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆127Updated 2 years ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆72Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆206Updated 6 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆35Updated 11 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆182Updated 2 years ago
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆26Updated last month
• METR / task-standard
  METR Task Standard
  ☆151Updated 5 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆53Updated 2 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆255Updated 11 months ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆230Updated 5 months ago
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆14Updated 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 …
  ☆192Updated this week
• saprmarks / dictionary_learning
  ☆314Updated last month
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆605Updated this week
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆207Updated this week
• redwoodresearch / Easy-Transformer
  ☆121Updated 11 months ago
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆51Updated 3 years ago
• redwoodresearch / rust_circuit_public
  ☆63Updated 2 years ago
• ARBORproject / arborproject.github.io
  ☆78Updated 4 months ago
• collin-burns / discovering_latent_knowledge
  ☆273Updated last year
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆73Updated this week
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 5 months ago