Locating and editing factual associations in GPT (NeurIPS 2022)

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

Attributing predictions made by the Inception network using the Integrated Gradients method

Code for the ACL-2022 paper "Knowledge Neurons in Pretrained Transformers"

CVPR 2021 | Metrics for evaluating interpretability methods.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.