@inproceedings{shu-etal-2025-beyond,
    title = "Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders",
    author = "Shu, Dong  and
      Wu, Xuansheng  and
      Zhao, Haiyan  and
      Du, Mengnan  and
      Liu, Ninghao",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.87/",
    pages = "1673--1682",
    ISBN = "979-8-89176-332-6",
    abstract = "Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on input-side activations, without considering the influence between each latent feature and the model{'}s output. This work is built on two key hypotheses: (1) activated latents do not contribute equally to the construction of the model{'}s output, and (2) only latents with high influence are effective for model steering. To validate these hypotheses, we propose Gradient Sparse Autoencoder (GradSAE), a simple yet effective method that identifies the most influential latents by incorporating output-side gradient information."
}