English
Related papers

Related papers: From Flat to Hierarchical: Extracting Sparse Repre…

200 papers

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

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets

Sparse Autoencoders (SAEs) have emerged as a useful tool for interpreting the internal representations of neural networks. However, naively optimising SAEs for reconstruction loss and sparsity results in a preference for SAEs that are…

Machine Learning · Computer Science 2024-10-16 Kola Ayonrinde , Michael T. Pearce , Lee Sharkey

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) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In this work, we conduct a comprehensive analysis of how vision…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…

Machine Learning · Computer Science 2026-05-28 Tue M. Cao , Nguyen Do , My T. Thai

The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…

Machine Learning · Computer Science 2026-01-29 Chiraag Kaushik , Davis Barch , Andrea Fanelli

Understanding how features evolve across layers in deep neural networks is a fundamental challenge in mechanistic interpretability, particularly due to polysemanticity and feature superposition. While Sparse Autoencoders (SAEs) have been…

Machine Learning · Computer Science 2025-03-04 Nikita Balagansky , Ian Maksimov , Daniil Gavrilov

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

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

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

It is assumed that sparse autoencoders (SAEs) decompose polysemantic activations into interpretable linear directions, as long as the activations are composed of sparse linear combinations of underlying features. However, we find that if an…

Machine Learning · Computer Science 2025-09-29 David Chanin , Tomáš Dulka , Adrià Garriga-Alonso

Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions. In image classification, these models typically recover human-interpretable concepts from an image and…

Machine Learning · Computer Science 2026-03-31 Nghia Nguyen , Tianjiao Ding , René Vidal

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Thomas Fel , Ekdeep Singh Lubana , Jacob S. Prince , Matthew Kowal , Victor Boutin , Isabel Papadimitriou , Binxu Wang , Martin Wattenberg , Demba Ba , Talia Konkle

Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine additively through linear reconstruction, an assumption that…

Machine Learning · Computer Science 2026-05-26 Panagiotis Koromilas , Andreas D. Demou , James Oldfield , Yannis Panagakis , Mihalis Nicolaou

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

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