diagNNose: A Library for Neural Activation Analysis
2020-11-13EMNLP (BlackboxNLP) 2020Code Available1· sign in to hype
Jaap Jumelet
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/i-machine-think/diagnnoseOfficialIn paperpytorch★ 81
Abstract
In this paper we introduce diagNNose, an open source library for analysing the activations of deep neural networks. diagNNose contains a wide array of interpretability techniques that provide fundamental insights into the inner workings of neural networks. We demonstrate the functionality of diagNNose with a case study on subject-verb agreement within language models. diagNNose is available at https://github.com/i-machine-think/diagnnose.