标题： NeuroSurgeon：用于子网络分析的工具包 显示英文标题

标题： NeuroSurgeon: A Toolkit for Subnetwork Analysis

摘要： 尽管在可解释性领域取得了最近的进展，关于神经网络学习表示的算法仍有许多未知之处。 最近的工作尝试通过将模型分解为功能电路来理解训练后的模型（Csordás等，2020；Lepori等，2023）。 为了推进这项研究，我们开发了NeuroSurgeon，这是一个Python库，可用于发现和操作Huggingface Transformers库中的模型内的子网络。 NeuroSurgeon可在https://github.com/mlepori1/NeuroSurgeon免费获得。 显示英文摘要

摘要： Despite recent advances in the field of explainability, much remains unknown about the algorithms that neural networks learn to represent. Recent work has attempted to understand trained models by decomposing them into functional circuits (Csord\'as et al., 2020; Lepori et al., 2023). To advance this research, we developed NeuroSurgeon, a python library that can be used to discover and manipulate subnetworks within models in the Huggingface Transformers library (Wolf et al., 2019). NeuroSurgeon is freely available at https://github.com/mlepori1/NeuroSurgeon.