personal account \\ @anthropics \\ previously: @google-deepmind
Repositories
ArthurConmy/sae
ArthurConmy/hereditary
ArthurConmy/arthurconmy.github.io
Personal website
ArthurConmy/hereditary-gemma-depression-quickstart
ArthurConmy/polymarket-toolbar
Futarchy in front of you
ArthurConmy/safety-tooling
Inference API for many LLMs and other useful tools for empirical research
ArthurConmy/SAELens
Training Sparse Autoencoders on Language Models
ArthurConmy/jaxtyping
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
ArthurConmy/ai-psychosis
ArthurConmy/PracticalSessions2025
ArthurConmy/chainscope
Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper
ArthurConmy/MishformerLens
MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing a custom, numerically inaccurate Transformer architecture.
ArthurConmy/SAE-TS
Improving Steering Vectors by Targeting Sparse Autoencoder Features
ArthurConmy/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
ArthurConmy/TransformerLens
ArthurConmy/sae_vis
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
ArthurConmy/fancyflags-minimal-example
ArthurConmy/cam-notes
My Cambridge Lecture Notes
ArthurConmy/grok
ArthurConmy/sparse_autoencoder
Sparse Autoencoder for Mechanistic Interpretability
ArthurConmy/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
ArthurConmy/SERI-MATS-2023-Streamlit-pages
Repo for hosting Streamlit pages for my 2023 SERI MATS project with Arthur Conmy (mentored by Neel Nanda).
ArthurConmy/chef-transformer
Chef Transformer 🍲 .
ArthurConmy/rust_circuit_public
ArthurConmy/Hackbridge
ArthurConmy/maths-tripos-questions
Archive of questions from the Cambridge Mathematics Tripos
ArthurConmy/ai-safety-gridworlds
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
ArthurConmy/CuAINLPWorkshop
ArthurConmy/L-BRGM
Implementation of the L-BRGM model from our paper https://arxiv.org/abs/2110.03814 (IEEE ICASSP 2022)