English
Related papers

Related papers: Mechanistic Interpretability with Sparse Autoencod…

200 papers

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) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

Machine Learning · Computer Science 2025-11-19 Ashwin Saraswatula , David Klindt

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

Previous studies primarily utilize MLP neurons as units of analysis for understanding the mechanisms of factual knowledge in Language Models (LMs); however, neurons suffer from polysemanticity, leading to limited knowledge expression and…

Computation and Language · Computer Science 2025-02-28 Yuheng Chen , Pengfei Cao , Kang Liu , Jun Zhao

Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training…

Computer Vision and Pattern Recognition · Computer Science 2017-04-28 Elyor Kodirov , Tao Xiang , Shaogang Gong

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mateusz Pach , Shyamgopal Karthik , Quentin Bouniot , Serge Belongie , Zeynep Akata

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Sound · Computer Science 2026-03-03 Nikhil Singh , Manuel Cherep , Pattie Maes

Neural operators have been validated as promising deep surrogate models for solving partial differential equations (PDEs). Despite the critical role of boundary conditions in PDEs, however, only a limited number of neural operators robustly…

Numerical Analysis · Mathematics 2023-12-13 Ziyuan Liu , Yuhang Wu , Daniel Zhengyu Huang , Hong Zhang , Xu Qian , Songhe Song

Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabulary, which might hinder performance (polysemicity and synonymy) and pose a challenge for…

Information Retrieval · Computer Science 2026-04-24 Yuxuan Zong , Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

The classical sparse coding model represents visual stimuli as a linear combination of a handful of learned basis functions that are Gabor-like when trained on natural image data. However, the Gabor-like filters learned by classical sparse…

Artificial Intelligence · Computer Science 2023-02-23 Jonathan Huml , Abiy Tasissa , Demba Ba

Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that mitigates these issues by converting NNs from weight space to function space, via a dual parameterization.…

Machine Learning · Statistics 2023-09-06 Aidan Scannell , Riccardo Mereu , Paul Chang , Ella Tamir , Joni Pajarinen , Arno Solin

Neural operators (NOs) provide a new paradigm for efficiently solving partial differential equations (PDEs), but their training depends on costly high-fidelity data from numerical solvers, limiting applications in complex systems. We…

Computational Physics · Physics 2026-05-18 Wen You , Shaoqian Zhou , Xuhui Meng

Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this joint space, and how do the models encode meaning and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Isabel Papadimitriou , Huangyuan Su , Thomas Fel , Sham Kakade , Stephanie Gil

Modeling high-frequency information is a critical challenge in scientific machine learning. For instance, fully turbulent flow simulations of the Navier-Stokes equations at Reynolds numbers 3500 and above can generate high-frequency signals…

Machine Learning · Computer Science 2026-01-13 Marimuthu Kalimuthu , David Holzmüller , Mathias Niepert

We propose the *State Space Neural Operator* (SS-NO), a compact architecture for learning solution operators of time-dependent partial differential equations (PDEs). Our formulation extends structured state space models (SSMs) to joint…

Machine Learning · Computer Science 2026-03-09 Nodens Koren , Samuel Lanthaler

Fourier Neural Operators (FNOs) excel on tasks using functional data, such as those originating from partial differential equations. Such characteristics render them an effective approach for simulating the time evolution of quantum…

Learning a generative model of visual information with sparse and compositional features has been a challenge for both theoretical neuroscience and machine learning communities. Sparse coding models have achieved great success in explaining…

Machine Learning · Computer Science 2021-01-26 Linxing Preston Jiang , Luciano de la Iglesia

Fourier Neural Operators (FNOs) have demonstrated exceptional accuracy in mapping functional spaces by leveraging Fourier transforms to establish a connection with underlying physical principles. However, their opaque inner workings often…

Fluid Dynamics · Physics 2025-11-04 Marco Cayuela , Vincent Le Chenadec , Peter Schmid , Taraneh Sayadi

We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and…

Machine Learning · Computer Science 2014-07-24 Sourav Bhattacharya , Petteri Nurmi , Nils Hammerla , Thomas Plötz

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