论文标题
诊断：神经激活分析的库
diagNNose: A Library for Neural Activation Analysis
论文作者
论文摘要
在本文中，我们介绍了诊断，这是一个开源库，用于分析深神经网络的激活。诊断包含各种各样的可解释性技术，可为神经网络的内部运作提供基本的见解。我们通过对语言模型中的主题 - 动词协议进行案例研究的诊断研究证明了诊断的功能。诊断可在https://github.com/i-machine-think/diagnnose上找到。
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.
