mlsanityData to 7 Oct 2026

NeuroSurgeon: A Toolkit for Subnetwork Analysis

arXiv 2309.00244 ↗First posted 1 Sep 2023cs.LG cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 22 of its 25 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

22 of 25 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  7. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,130
  8. 2022In-context Learning and Induction Headscited by 930
  9. 2023Progress measures for grokking via mechanistic interpretabilitycited by 822
  10. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 700
  11. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  12. 2020Parameter-Efficient Transfer Learning with Diff Pruningcited by 351
10 more
  1. 2023Task-Specific Skill Localization in Fine-tuned Language Modelscited by 104
  2. 2019Winning the Lottery with Continuous Sparsificationcited by 99
  3. 2020Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Maskscited by 97
  4. 2023Language Models Implement Simple Word2Vec-style Vector Arithmeticcited by 97
  5. 2021Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?cited by 75
  6. 2020How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Maskingcited by 63
  7. 2021Low-Complexity Probing via Finding Subnetworkscited by 63
  8. 2023Break It Down: Evidence for Structural Compositionality in Neural Networkscited by 44
  9. 2021Sparse Interventions in Language Models with Differentiable Maskingcited by 34
  10. 2023Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 1; 2026: 2.

9 papers.

  1. 2023Towards Best Practices of Activation Patching in Language Models: Metrics and Methodscited by 328
  2. 2024Knowledge Mechanisms in Large Language Models: A Survey and Perspectivecited by 50
  3. 2024Understanding Visual Feature Reliance through the Lens of Complexitycited by 15
  4. 2023Uncovering Intermediate Variables in Transformers using Circuit Probingcited by 12
  5. 2024Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objectscited by 12
  6. 2024The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Modelscited by 9
  7. 2025Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Modelscited by 5
  8. 2026Bi-Orthogonal Factor Decomposition for Vision Transformerscited by 4
  9. 2026BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcyclingcited by 0