Route Sparse Autoencoder to Interpret Large Language Models - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Wei Shi, Sihang Li 0002, Tao Liang, Mingyang Wan, Guojun Ma, Xiang Wang 0010, Xiangnan He 0001. Route Sparse Autoencoder to Interpret Large Language Models. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 6801-6815, Association for Computational Linguistics, 2025. [doi]

This author has not been identified. Look up 'Wei Shi' in GoogleThis author has not been identified. Look up 'Sihang Li 0002' in GoogleThis author has not been identified. Look up 'Tao Liang' in GoogleThis author has not been identified. Look up 'Mingyang Wan' in GoogleThis author has not been identified. Look up 'Guojun Ma' in GoogleThis author has not been identified. Look up 'Xiang Wang 0010' in GoogleThis author has not been identified. Look up 'Xiangnan He 0001' in Google

runs on WebDSL