English
Related papers

Related papers: Sparse, Geometric Autoencoder Models of V1

200 papers

Autoencoders are a prominent model in many empirical branches of machine learning and lossy data compression. However, basic theoretical questions remain unanswered even in a shallow two-layer setting. In particular, to what degree does a…

Machine Learning · Computer Science 2024-02-08 Kevin Kögler , Alexander Shevchenko , Hamed Hassani , Marco Mondelli

Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders…

Machine Learning · Computer Science 2024-06-07 Leo Gao , Tom Dupré la Tour , Henk Tillman , Gabriel Goh , Rajan Troll , Alec Radford , Ilya Sutskever , Jan Leike , Jeffrey Wu

Working in high-dimensional latent spaces, the internal encoding of data in Variational Autoencoders becomes naturally sparse. We discuss this known but controversial phenomenon sometimes refereed to as overpruning, to emphasize the…

Machine Learning · Computer Science 2019-02-14 Andrea Asperti

Sparse coding algorithms are about finding a linear basis in which signals can be represented by a small number of active (non-zero) coefficients. Such coding has many applications in science and engineering and is believed to play an…

Neural and Evolutionary Computing · Computer Science 2016-08-14 András Lőrincz , Zsolt Palotai , Gábor Szirtes

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal…

Machine Learning · Computer Science 2012-06-22 Alex Bronstein , Pablo Sprechmann , Guillermo Sapiro

Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational…

Machine Learning · Computer Science 2025-10-03 Zachary Baker , Yuxiao Li

The two-dimensional Gabor function is adapted to natural image statistics, leading to a tractable probabilistic generative model that can be used to model simple-cell receptive-field profiles, or generate basis functions for sparse coding…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Peter Loxley

We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical…

Machine Learning · Statistics 2019-02-18 Thanh V. Nguyen , Raymond K. W. Wong , Chinmay Hegde

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using $k$-sparse autoencoders lacks a theoretical grounding for selecting the…

Machine Learning · Computer Science 2025-08-11 Sewoong Lee , Adam Davies , Marc E. Canby , Julia Hockenmaier

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear directions. However, a growing body of…

Brain MRI foundation models learn rich representations of anatomy, but interpreting what clinical information they encode remains an open problem. Standard sparse autoencoders (SAEs) suffer from severe feature collapse in deep transformer…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Favour Nerrise , Lucy Yin , Mohammad H. Abbasi , Kilian M. Pohl , Ehsan Adeli

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

Machine Learning · Computer Science 2026-03-10 Vegard Flovik

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

We introduce an explainable generative model by applying sparse operation on the feature maps of the generator network. Meaningful hierarchical representations are obtained using the proposed generative model with sparse activations. The…

Machine Learning · Computer Science 2019-02-01 Xianglei Xing , Song-Chun Zhu , Ying Nian Wu

Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to…

Machine Learning · Computer Science 2025-06-04 Anish Mudide , Joshua Engels , Eric J. Michaud , Max Tegmark , Christian Schroeder de Witt

We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-organize, using only minimal supervision (labels for <0.1% of examples per anchored concept).…

Machine Learning · Computer Science 2026-04-28 Sandy Fraser , Patryk Wielopolski

Sparse Autoencoders (SAEs) are widely used to interpret neural networks by identifying meaningful concepts from their representations. However, do SAEs truly uncover all concepts a model relies on, or are they inherently biased toward…

Machine Learning · Computer Science 2025-12-03 Sai Sumedh R. Hindupur , Ekdeep Singh Lubana , Thomas Fel , Demba Ba

Convolutional Sparse Coding (CSC) is an increasingly popular model in the signal and image processing communities, tackling some of the limitations of traditional patch-based sparse representations. Although several works have addressed the…

Computer Vision and Pattern Recognition · Computer Science 2017-05-10 Vardan Papyan , Yaniv Romano , Jeremias Sulam , Michael Elad

A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…

Computer Vision and Pattern Recognition · Computer Science 2017-12-12 Dimitrios C. Gklezakos , Rajesh P. N. Rao

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Artificial Intelligence · Computer Science 2026-03-27 Yunpeng Zhou