English
Related papers

Related papers: Does higher interpretability imply better utility?…

200 papers

Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training hyperparameter is L0: how many SAE features should fire per token on average. Existing work…

Machine Learning · Computer Science 2025-12-08 David Chanin , Adrià Garriga-Alonso

Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic interpretability, particularly through…

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Philipp Wesp , Robbie Holland , Vasiliki Sideri-Lampretsa , Sergios Gatidis

We investigate whether sparse autoencoders (SAEs) can be used to remove knowledge from language models. We use the biology subset of the Weapons of Mass Destruction Proxy dataset and test on the gemma-2b-it and gemma-2-2b-it language…

Machine Learning · Computer Science 2024-11-05 Eoin Farrell , Yeu-Tong Lau , Arthur Conmy

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed…

Machine Learning · Computer Science 2026-03-05 Jingyi Cui , Qi Zhang , Yifei Wang , Yisen Wang

Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using…

Machine Learning · Computer Science 2025-04-21 Dmitrii Kharlapenko , Stepan Shabalin , Fazl Barez , Arthur Conmy , Neel Nanda

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Information Retrieval · Computer Science 2026-01-19 Martin Spišák , Ladislav Peška , Petr Škoda , Vojtěch Vančura , Rodrigo Alves

Radiological services are experiencing unprecedented demand, leading to increased interest in automating radiology report generation. Existing Vision-Language Models (VLMs) suffer from hallucinations, lack interpretability, and require…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Ahmed Abdulaal , Hugo Fry , Nina Montaña-Brown , Ayodeji Ijishakin , Jack Gao , Stephanie Hyland , Daniel C. Alexander , Daniel C. Castro

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting language model activations by decomposing them into sparse, interpretable features. A popular approach is the TopK SAE, that uses a fixed number of the most active…

Machine Learning · Computer Science 2024-12-10 Bart Bussmann , Patrick Leask , Neel Nanda

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Computation and Language · Computer Science 2025-06-02 Xu Wang , Zihao Li , Benyou Wang , Yan Hu , Difan Zou

Large Language Models (LLMs) are trained on massive, unstructured corpora, making it unclear which social patterns and biases they absorb and later reproduce. Existing evaluations typically examine outputs or activations, but rarely connect…

Computation and Language · Computer Science 2025-11-14 Mariam Mahran , Katharina Simbeck

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

As machine learning models are increasingly deployed in high-stakes domains, the need for interpretability has grown to meet strict regulatory and accountability constraints. Despite this interest, systematic evaluations of inherently…

Machine Learning · Computer Science 2026-03-27 Mattia Billa , Giovanni Orlandi , Veronica Guidetti , Federica Mandreoli

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Zhenyu Lu , Liupeng Li , Jinpeng Wang , Haoqian Kang , Yan Feng , Ke Chen , Yaowei Wang

While mechanistic interpretability tools like Sparse Autoencoders (SAEs) can uncover meaningful features within Large Language Models (LLMs), a critical gap remains in transforming these insights into practical actions for model…

Artificial Intelligence · Computer Science 2026-04-29 Ling Shi , Xinwei Wu , Xiaohu Zhao , Hao Wang , Heng Liu , Yangyang Liu , Linlong Xu , Longyue Wang , Deyi Xiong , Weihua Luo

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

Sparse autoencoders (SAEs) are a promising approach to extracting features from neural networks, enabling model interpretability as well as causal interventions on model internals. SAEs generate sparse feature representations using a…

Machine Learning · Computer Science 2024-11-11 Kola Ayonrinde

Large Language Models (LLMs) have achieved remarkable success across many applications, with Mixture of Experts (MoE) models demonstrating great potential. Compared to traditional dense models, MoEs achieve better performance with less…

Machine Learning · Computer Science 2026-02-17 Zongle Huang , Lei Zhu , Zongyuan Zhan , Ting Hu , Weikai Mao , Xianzhi Yu , Yongpan Liu , Tianyu Zhang