English
Related papers

Related papers: Structuring Autoencoders

200 papers

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

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

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been…

Machine Learning · Computer Science 2024-05-27 Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Machine Learning · Computer Science 2024-09-10 Liv Gorton

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

Machine Learning · Computer Science 2025-05-29 Wenjie Sun , Bingzhe Wu , Zhile Yang , Chengke Wu

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Machine Learning · Computer Science 2025-07-14 Gonçalo Paulo , Nora Belrose

Modern LLMs face inference efficiency challenges due to their scale. To address this, many compression methods have been proposed, such as pruning and quantization. However, the effect of compression on a model's interpretability remains…

Machine Learning · Computer Science 2025-07-23 Suchit Gupte , Vishnu Kabir Chhabra , Mohammad Mahdi Khalili

Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter…

Machine Learning · Computer Science 2026-05-07 Chris Sainsbury , Feng Dong , Andreas Karwath

Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce…

Machine Learning · Computer Science 2024-02-19 Mohammad Hossein Amani , Nicolas Mario Baldwin , Amin Mansouri , Martin Josifoski , Maxime Peyrard , Robert West

Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing counting model training. Some sophisticated noise-resistance…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Yuda Zou , Xin Xiao , Peilin Zhou , Zhichao Sun , Bo Du , Yongchao Xu

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

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Computation and Language · Computer Science 2025-06-10 Jiaming Li , Haoran Ye , Yukun Chen , Xinyue Li , Lei Zhang , Hamid Alinejad-Rokny , Jimmy Chih-Hsien Peng , Min Yang

Detecting navigable space is the first and also a critical step for successful robot navigation. In this work, we treat the visual navigable space segmentation as a scene decomposition problem and propose a new network, NSS-VAEs (Navigable…

Robotics · Computer Science 2021-11-03 Zheng Chen , Lantao Liu

In contrast to fully-supervised models, self-supervised representation learning only needs a fraction of data to be labeled and often achieves the same or even higher downstream performance. The goal is to pre-train deep neural networks on…

Machine Learning · Computer Science 2025-04-09 Friederike Baier , Sebastian Mair , Samuel G. Fadel

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

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

Machine Learning · Computer Science 2026-02-04 Anika Shrivastava , Renu Rameshan , Samar Agnihotri

Neural Networks play a growing role in many science disciplines, including physics. Variational Autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional…

Machine Learning · Statistics 2021-12-08 Johannes Zacherl , Philipp Frank , Torsten A. Enßlin

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual…

Computer Vision and Pattern Recognition · Computer Science 2018-11-02 Gabriel B. Cavallari , Leonardo Sampaio Ferraz Ribeiro , Moacir Antonelli Ponti

We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks. The learning of the representations is…

Machine Learning · Computer Science 2015-11-24 Henry W J Reeve , Gavin Brown

Autoencoder can give rise to an appropriate latent representation of the input data, however, the representation which is solely based on the intrinsic property of the input data, is usually inferior to express some semantic information. A…

Machine Learning · Computer Science 2022-06-01 Yurui Ming , Cuihuan Du , Chin-Teng Lin