mlsanityData to 7 Oct 2026

The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning

arXiv 2602.23993 ↗First posted 27 Feb 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate gradiend through an English pronoun running example, a semantic sentiment use case that evaluates lexical generalization to held-out target words, and a large-scale feature comparison.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 27 Feb 2026.

Builds on

18 of 29 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  5. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  6. 2022Mass-Editing Memory in a Transformercited by 976
  7. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  8. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 414
  9. 2023Towards Best Practices of Activation Patching in Language Models: Metrics and Methodscited by 328
  10. 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 209
  11. 2013Crowdsourcing a Word-Emotion Association Lexiconcited by 193
  12. 2020The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Modelscited by 125
6 more
  1. 2023Inseq: An Interpretability Toolkit for Sequence Generation Modelscited by 78
  2. 2024pyvene: A Library for Understanding and Improving PyTorch Models via Interventionscited by 53
  3. 2024NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internalscited by 43
  4. 2025Steering Language Models with Weight Arithmeticcited by 19
  5. 2025GRADIEND: Feature Learning within Neural Networks Exemplified through Biasescited by 2
  6. 2026Understanding or Memorizing? A Case Study of German Definite Articles in Language Modelscited by 1

Built on by

Not cited yet.