diagNNose: A Library for Neural Activation Analysis
arXiv:2011.06819
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.
Accepted to the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, EMNLP 2020