The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GRADIEND: Monosemantic Feature Learning within Neural Networks Applied to Gender Debiasing of Transformer Models
AI systems frequently exhibit and amplify social biases, including gender bias, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to …
Decoderpath_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting
We present path_boost, a Python package for interpretable supervised learning on graph-structured input data. The package implements PathBoost, a gradient boosting algorithm that automatically discovers predictive labele…
Molecular Property PredictionBinary ClassificationGraph Neural Networklibact: Pool-based Active Learning in Python
libact is a Python package designed to make active learning easier for general users. The package not only implements several popular active learning strategies, but also features the active-learning-by-learning meta-alg…
Active LearningTangent: Automatic Differentiation Using Source Code Transformation in Python
Automatic differentiation (AD) is an essential primitive for machine learning programming systems. Tangent is a new library that performs AD using source code transformation (SCT) in Python. It takes numeric functions wr…
BIG-bench Machine LearningTextDescriptives: A Python package for calculating a large variety of metrics from text
TextDescriptives is a Python package for calculating a large variety of metrics from text. It is built on top of spaCy and can be easily integrated into existing workflows. The package has already been used for analysing…