Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.

Interpretability for sequence generation models 🐛 🔍

Not enough friends to play sporz? No worries, with that auto-gm you can save 1 player!

A library for activation patching based on nnsight.

A Python library of interactive CLI elements you have been looking for

A compositional diagramming and animation library as an eDSL in Python

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Making Transformers Obvious

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/l…

discord bot for sporz game

A Munch is a Python dictionary that provides attribute-style access (a la JavaScript objects).

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

🤖🌊 aiFlows: The building blocks of your collaborative AI

Argument Parser for Modern C++

The nnsight package enables interpreting and manipulating the internals of deep learned models.

🔏 Safe inference using representation engineering.

Quick GM dashboard help for http:https://www.sporz.fr/

A command-line benchmarking tool

A tool to solve systems of XOR equations

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Turn (almost) any Python command line program into a full GUI application with one line

Code for the paper "Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition"

Using Proximal Policy Optimization and Random Network Distillation on Pommerman

An attempt at making our own reinforcement learning-based Pommerman agents

💣 Bomberman deep reinforcement learning challenge in PyTorch