Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Uddin, Mohammed Mudassir, Alam, Shahnawaz, Pasha, Mohammed Kaif
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.12879