English
Related papers

Related papers: Do Sparse Autoencoders Generalize? A Case Study of…

200 papers

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Computation and Language · Computer Science 2025-02-24 Xuansheng Wu , Jiayi Yuan , Wenlin Yao , Xiaoming Zhai , Ninghao Liu

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier

Sparse autoencoders (SAEs) are a promising approach for uncovering interpretable features in large language models (LLMs). While several automated evaluation methods exist for SAEs, most rely on external LLMs. In this work, we introduce…

Computation and Language · Computer Science 2025-09-30 Alex Gulko , Yusen Peng , Sachin Kumar

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores the application of…

Machine Learning · Computer Science 2025-02-14 Edith Natalia Villegas Garcia , Alessio Ansuini

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Sparse Autoencoders (SAEs) can efficiently identify candidate monosemantic features from pretrained neural networks for galaxy morphology. We demonstrate this on Euclid Q1 images using both supervised (Zoobot) and new self-supervised (MAE)…

Instrumentation and Methods for Astrophysics · Physics 2025-11-13 John F. Wu , Michael Walmsley

Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability.…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the…

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits…

Computation and Language · Computer Science 2025-06-03 Mark Muchane , Sean Richardson , Kiho Park , Victor Veitch

Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms behind these reasoning processes remain unexplored. We…

Computation and Language · Computer Science 2025-08-07 Andrey Galichin , Alexey Dontsov , Polina Druzhinina , Anton Razzhigaev , Oleg Y. Rogov , Elena Tutubalina , Ivan Oseledets

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a…

Machine Learning · Computer Science 2026-03-31 Vitória Barin Pacela , Shruti Joshi , Isabela Camacho , Simon Lacoste-Julien , David Klindt

Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Vision Transformers (ViTs). By decomposing polysemantic…

Machine Learning · Computer Science 2026-05-11 Jakub Stępień , Marcin Mazur , Jacek Tabor , Przemysław Spurek

The hypothesis of Universality in interpretability suggests that different neural networks may converge to implement similar algorithms on similar tasks. In this work, we investigate two mainstream architectures for language modeling,…

Computation and Language · Computer Science 2024-10-11 Junxuan Wang , Xuyang Ge , Wentao Shu , Qiong Tang , Yunhua Zhou , Zhengfu He , Xipeng Qiu

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Hyesu Lim , Jinho Choi , Jaegul Choo , Steffen Schneider

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these…

Machine Learning · Computer Science 2025-02-10 Patrick Leask , Bart Bussmann , Michael Pearce , Joseph Bloom , Curt Tigges , Noura Al Moubayed , Lee Sharkey , Neel Nanda

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

Machine Learning · Computer Science 2025-05-20 Jeremy Budd , Javier Ideami , Benjamin Macdowall Rynne , Keith Duggar , Randall Balestriero

Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics,…

Machine Learning · Computer Science 2024-12-02 Adam Karvonen , Can Rager , Samuel Marks , Neel Nanda

Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied…

Machine Learning · Statistics 2026-03-05 Piotr Jedryszek , Oliver M. Crook

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi
‹ Prev 1 4 5 6 7 8 10 Next ›