astroautomata/SymTorch

Model interpretability and understanding for PyTorch

PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.

Symbolic Learning in Python and Julia

A game theoretic approach to explain the output of any machine learning model.

Public facing deeplift repo

Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]

👋 Xplique is a Neural Networks Explainability Toolbox

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

Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.