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

arXiv: https://arxiv.org/abs/2602.23993 · HTML: https://mlsanity.com/paper/2602.23993/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models](https://mlsanity.com/paper/2008.05122/) (2020)
- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [pyvene: A Library for Understanding and Improving PyTorch Models via Interventions](https://mlsanity.com/paper/2403.07809/) (2024)
- [NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals](https://mlsanity.com/paper/2407.14561/) (2024)
- [Steering Language Models with Weight Arithmetic](https://mlsanity.com/paper/2511.05408/) (2025)
- [GRADIEND: Feature Learning within Neural Networks Exemplified through Biases](https://mlsanity.com/paper/2502.01406/) (2025)
- [Understanding or Memorizing? A Case Study of German Definite Articles in Language Models](https://mlsanity.com/paper/2601.09313/) (2026)

## Built on by (most cited first, 1 of 1)

- [Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models](https://mlsanity.com/paper/2609.32355/) (2026)

## 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.