Butanium
Follow
-
nnterp Public
Unified access to Large Language Model modules using NNsight
-
Clash-of-bits Public
A multiplayer CodinGame contribution inspired by Gladiabots
-
PersonalityTraining Public
Forked from maiush/PersonalityTrainingsister repo to https://github.com/maiush/CharacterTraining
Jupyter Notebook UpdatedJul 29, 2025 -
-
-
tiny-activation-dashboard Public
A tiny easily hackable implementation of a feature dashboard.
-
butanium.github.io Public
Personal webpage, forked from mmistakes/minimal-mistakes
HTML MIT License UpdatedJun 26, 2025 -
-
-
-
-
DecompositionFaithfulnessPaper Public
Forked from anthropics/DecompositionFaithfulnessPaperPython UpdatedJan 8, 2025 -
nnsight Public
Forked from ndif-team/nnsightThe nnsight package enables interpreting and manipulating the internals of deep learned models.
Jupyter Notebook MIT License UpdatedDec 18, 2024 -
llm-lang-agnostic Public
minimal code to reproduce results from Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
-
llm-latent-language Public
Forked from epfl-dlab/llm-latent-language -
SAELens Public
Forked from jbloomAus/SAELensTraining Sparse Autoencoders on Language Models
Jupyter Notebook MIT License UpdatedOct 24, 2024 -
Real-Time-SParadox Public
A game written in Scala as part of our curriculum at the ENS
-
Awesome-Interpretability-in-Large-Language-Models Public
Forked from ruizheliUOA/Awesome-Interpretability-in-Large-Language-ModelsThis repository collects all relevant resources about interpretability in LLMs
Creative Commons Zero v1.0 Universal UpdatedJul 5, 2024 -
dlab-runai-images Public
Forked from jkminder/dlab-runai-imagesImages for RUNAI
Shell UpdatedJul 2, 2024 -
TransformerLens Public
Forked from TransformerLensOrg/TransformerLensA library for mechanistic interpretability of GPT-style language models
Python MIT License UpdatedMay 15, 2024 -
munch Public
Forked from Infinidat/munchA Munch is a Python dictionary that provides attribute-style access (a la JavaScript objects).
Python MIT License UpdatedApr 16, 2024 -
PPO-RND-Pommerman Public
Forked from CaptainE/PPO-RND-PommermanUsing Proximal Policy Optimization and Random Network Distillation on Pommerman
Jupyter Notebook UpdatedMar 24, 2024 -
-
-
geometry-of-truth Public
Forked from saprmarks/geometry-of-truth -
-
SuperSuit Public
Forked from Farama-Foundation/SuperSuitA collection of wrappers for Gymnasium and PettingZoo environments (being merged into gymnasium.wrappers and pettingzoo.wrappers
Python Other UpdatedJan 17, 2024 -
-
-
cleanrl Public
Forked from vwxyzjn/cleanrlHigh-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)