Alternatives and similar repositories for leela-interp

Users that are interested in leela-interp are comparing it to the libraries listed below

• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆117Updated 5 months ago
• understanding-search / maze-transformer
  This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
  ☆32Updated last month
• andyljones / boardlaw
  Scaling scaling laws with board games.
  ☆54Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆131Updated 3 years ago
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆106Updated 2 weeks ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆196Updated 2 years ago
• oli-clive-griffin / crosscode
  A library for training crosscoders
  ☆13Updated 6 months ago
• bilal-chughtai / rep-theory-mech-interp
  ☆27Updated 2 years ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆80Updated 3 years ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 7 months ago
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆14Updated last year
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆89Updated 2 years ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆74Updated 2 years ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 10 months ago
• ssokota / mec
  Code for minimum-entropy coupling.
  ☆32Updated 2 weeks ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆33Updated 6 months ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆25Updated 11 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆53Updated 3 years ago
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• neoneye / arc-dataset-collection
  Multiple datasets for ARC (Abstraction and Reasoning Corpus)
  ☆85Updated 8 months ago
• keyonvafa / world-model-evaluation
  ☆72Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• anthropics / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆201Updated 3 years ago
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆15Updated last month
• da-fr / arc-prize-2024
  Our solution for the arc challenge 2024
  ☆185Updated 5 months ago
• noanabeshima / matryoshka-saes
  ☆25Updated last year
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆20Updated 10 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆31Updated last year