Repository · GitHub

hila-chefer/Transformer-Explainability

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

View on GitHubReport an issue

Owner	hila-chefer
License (as declared)	MIT
Stars	2,019
Forks	260
Main language	Jupyter Notebook
Created	23 November 2020
Last updated at source	24 January 2024

jupyter notebookattention-matrixattention-visualizationbertbert-modelcvpr2021deep-learningexplainabilityperturbationtransformer-interpretabilityvision-transformervisualize-classificationsvit

Embed this entry

<iframe src="https://silytics.si/embed/item/a8e5b35b-64dc-4bc1-aa84-acb1501a4cc0" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.