diagNNose: A Library for Neural Activation Analysis

EMNLP (BlackboxNLP) 2020  ·  Jaap Jumelet ·

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.

PDF Abstract EMNLP (BlackboxNLP) 2020 PDF EMNLP (BlackboxNLP) 2020 Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods