How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
A toolbox to iNNvestigate neural networks' predictions!
This repository contains a sample implementation of Gradient Feature Auditing (GFA) meant to be generalizable to most datasets. For more information on the repair process, see our paper on Certifying and Removing Disparate Impact. For information on the full auditing process, see our paper on…
Project Page // Paper // No-code Web Demo // Colab Notebook
GIM (Gradient Interaction Modifications) is a state-of-the-art feature attribution method and circuit discovery method. It currently leads the leaderboard for the Mechanistic Interpretability Benchmark, while being as fast as gradients.
The main features of joakimedin/gim are: Explainable AI Libraries.
Projects with overlapping indexed features include: albermax/innvestigate — A toolbox to iNNvestigate neural networks' predictions! algofairness/blackboxauditing — This repository contains a sample implementation of Gradient Feature Auditing (GFA) meant to be generalizable to most… alvinwan/neural-backed-decision-trees — Project Page // Paper // No-code Web Demo // Colab Notebook. andosa/treeinterpreter — TreeInterpreter. ankurtaly/integrated-gradients — (a.k.a. Path-Integrated Gradients, a.k.a. Axiomatic Attribution for Deep Networks). aerdem4/lofo-importance — Leave One Feature Out Importance.
