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

arXiv:2602.23993 · cs.CL · Submitted 2026-02-27 · Read on arXiv

cs.CL

Submitted: 2026-02-27

Updated: 2026-09-06

Comments: Accepted at EMNLP 2026 System Demonstrations

Code: https://github.com/aieng-lab/gradiend

Project page: https://aieng-lab.github.io/gradiend

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Pruning — 29× in this paper · explained in 4 episodes
Interpretability — 8× in this paper · explained in 15 episodes
Ablation — 5× in this paper · explained in 1 episode
Generalization — 5× in this paper · explained in 13 episodes
Core — 4× in this paper · explained in 2 episodes
Steering — 4× in this paper · explained in 2 episodes
Transformer — 4× in this paper · explained in 2 episodes
Feature Selection — 3× in this paper · explained in 4 episodes
Abstraction — 2× in this paper · explained in 1 episode
Adam — 2× in this paper · explained in 2 episodes
Fine-Tuning — 2× in this paper · explained in 5 episodes
Language Modeling Score — 2× in this paper
Activation Patching — 1× in this paper · explained in 2 episodes
Benchmark — 1× in this paper · explained in 2 episodes
Foundation Model — 1× in this paper · explained in 3 episodes

Sources

Related papers