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 on an English pronoun paradigm and on a large-scale feature comparison that reproduces prior use cases.
@article{arxiv.2602.23993,
title = {The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning},
author = {Jonathan Drechsel and Steffen Herbold},
journal= {arXiv preprint arXiv:2602.23993},
year = {2026}
}