Lists (3)
Stars
Sparse Autoencoder for Mechanistic Interpretability
Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
Implementation of Alphafold 3 from Google Deepmind in Pytorch
Predict the whole sequence and 3D structure of masked protein sequences with ESM by @evolutionaryscale
Croissant is a high-level format for machine learning datasets that brings together four rich layers.
Sparsify transformers with SAEs and transcoders
ProtMamba: a homology-aware but alignment-free protein state space model
An open-source platform for developing protein models beyond AlphaFold.
Implementation of Alpha Fold 3 from the paper: "Accurate structure prediction of biomolecular interactions with AlphaFold3" in PyTorch
The hub for EleutherAI's work on interpretability and learning dynamics
JupyterLab spreadsheet editor for tabular data (e.g. csv, tsv)
Training Sparse Autoencoders on Language Models
A library for mechanistic interpretability of GPT-style language models
👋 Xplique is a Neural Networks Explainability Toolbox
A collection of infrastructure and tools for research in neural network interpretability.
[ICML 2022] Representation Topology Divergence: A Method for Comparing Neural Network Representations
Package to generate synthetic data from the bascule generative model.
Processing Library and Analysis Toolkit for Medical Imaging in Python