ArthurConmy

Automatic-Circuit-Discovery

sae

arthurconmy.github.io

Personal website

cam-notes

My Cambridge Lecture Notes

grok

ai-safety-gridworlds

This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.

chef-transformer

Chef Transformer 🍲 .

CuAINLPWorkshop

EPQ

Hackbridge

L-BRGM

Implementation of the L-BRGM model from our paper https://arxiv.org/abs/2110.03814 (IEEE ICASSP 2022)

maths-tripos-questions

Archive of questions from the Cambridge Mathematics Tripos

fancyflags-minimal-example

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

mlab

Machine Learning for Alignment Bootcamp

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Q-Sharp-Codeforces-Contests

Repository containing assorted solutions to the various Q# contests hosted on codeforces (and associated tutorials)

rust_circuit_public

sae_vis

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

SERI-MATS-2023-Streamlit-pages

Repo for hosting Streamlit pages for my 2023 SERI MATS project with Arthur Conmy (mentored by Neel Nanda).

sparse_autoencoder

Sparse Autoencoder for Mechanistic Interpretability

TLE

🤖 Discord Bot for Competitive Programming

TransformerLens