Learning Interpretability Tool (LIT)

A visual, interactive model-understanding and data visualization tool.

You can use open-source LIT to interpret models or to visualize text, image, and tabular data.

Created for this library

1.
A research team uses the Learning Interpretability Tool to explore prediction explanations side by side for several model variants.
2.
An NLP team uses the Learning Interpretability Tool to inspect attention and saliency maps on misclassified examples.
3.
A startup uses the Learning Interpretability Tool as a shared review environment during model release walkthroughs.

Loading…