Multi-Agent Harness for Production AI

AI agents running research on single-GPU nanochat training automatically

Visualizing query-key interactions in language + vision transformers (VIS 2023)

👋 Overcomplete is a Vision-based SAE Toolbox

ThreeDWorld simulation environment

State control system for automated behavioral training

Database for experimental neuroscience laboratories

NeurIPS | 1st place solution for Sensorium 2023 Competition

A toolbox for integrated information theory.

Fast spike sorting with drift correction

GPU code for spike sorting

Open standard for machine learning interoperability

SiBBlInGS framework code

Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE benchmark with subquadratic complexity in length (or without…

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Visualize features cells are responsive to via gradient ascent.

Reconstructing visual stimuli shown to mice from two-photon neural recordings

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

Codebase for testing whether hidden states of neural networks encode discrete structures.

The standardised environment for the hippocampus and entorhinal cortex models

A PyTorch implementation of Latent Factor Analysis via Dynamical Systems (LFADS) and AutoLFADS.

Code for recreating the figures in the brainrender paper (Claudi et al. 2020)

A simple tool for zebrafish brain visualization.

Representation Engineering: A Top-Down Approach to AI Transparency

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"