mlsanityData to 7 Oct 2026

Interpreto: An Explainability Library for Transformers

arXiv 2512.09730 ↗First posted 10 Dec 2025cs.CL cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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. See GitHub: https://github.com/FOR-sight-ai/interpreto and the demo website: https://for-sight-ai.github.io/interpreto-demo/.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 47 of its 76 references that are in the map. First posted on arXiv 10 Dec 2025.

Builds on

47 of 76 references.

References · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  8. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  9. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  11. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
35 more
  1. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  2. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  3. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  4. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  5. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  6. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  7. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 831
  8. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  9. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  10. 2023The Falcon Series of Open Language Modelscited by 526
  11. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  12. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 522
  13. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  14. 2024Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoderscited by 283
  15. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 199
  16. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  17. 2020Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectorscited by 119
  18. 2025SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretabilitycited by 118
  19. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
  20. 2023Inseq: An Interpretability Toolkit for Sequence Generation Modelscited by 78
  21. 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Modelscited by 67
  22. 2021Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysiscited by 65
  23. 2024pyvene: A Library for Understanding and Improving PyTorch Models via Interventionscited by 53
  24. 2025From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuitcited by 45
  25. 2025Enhancing Automated Interpretability with Output-Centric Feature Descriptionscited by 39
  26. 2024Towards Unifying Interpretability and Control: Evaluation via Interventioncited by 28
  27. 2022ferret: a Framework for Benchmarking Explainers on Transformerscited by 26
  28. 2022Xplique: A Deep Learning Explainability Toolboxcited by 24
  29. 2025Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Videocited by 20
  30. 2023COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP taskscited by 16
  31. 2025FADE: Why Bad Descriptions Happen to Good Featurescited by 13
  32. 2025ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatabilitycited by 9
  33. 2023TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributescited by 4
  34. 2025nnterp: A Standardized Interface for Mechanistic Interpretability of Transformerscited by 2
  35. 2025There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformerscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanationscited by 0