{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neurosurgeon-a-toolkit-for-subnetwork","title":"NeuroSurgeon: A Toolkit for Subnetwork Analysis","arxiv_id":"2309.00244","date":"2023-09-01","proceeding":null,"authors":["Michael A. Lepori","Ellie Pavlick","Thomas Serre"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2309.00244v1","url_pdf":"https://arxiv.org/pdf/2309.00244v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neurosurgeon-a-toolkit-for-subnetwork","repo_url":"https://github.com/mlepori1/neurosurgeon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2309.00244","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}