Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs. It provides two complementary families of methods: attribution methods and concept-based explanations. The library bridges recent research and practical tooling by exposing explanation workflows through a unified API for both classification and text generation. A key differentiator is its end-to-end concept-based pipeline (from activation extraction to concept learning, interpretation, and scoring), which goes beyond feature-level attributions and is uncommon in existing libraries.
Cite
@article{arxiv.2512.09730,
title = {Interpreto: An Explainability Library for Transformers},
author = {Antonin Poché and Thomas Mullor and Gabriele Sarti and Frédéric Boisnard and Corentin Friedrich and Charlotte Claye and François Hoofd and Raphael Bernas and Céline Hudelot and Fanny Jourdan},
journal= {arXiv preprint arXiv:2512.09730},
year = {2026}
}