English
Related papers

Related papers: Sparse Autoencoders Enable Scalable and Reliable C…

200 papers

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Fabian Morelli , Arnas Uselis , Ankit Sonthalia , Seong Joon Oh

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Computation and Language · Computer Science 2025-07-01 Ananya Joshi , Celia Cintas , Skyler Speakman

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan

Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…

Machine Learning · Computer Science 2025-11-13 Ege Erdogan , Ana Lucic

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…

Machine Learning · Statistics 2017-03-07 Matt J. Kusner , Brooks Paige , José Miguel Hernández-Lobato

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…

Machine Learning · Computer Science 2026-02-13 Hakaze Cho , Haolin Yang , Yanshu Li , Brian M. Kurkoski , Naoya Inoue

Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and…

Machine Learning · Computer Science 2014-03-25 Alireza Makhzani , Brendan Frey

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the internal representations of large language models (LLMs), revealing latent latent features with semantical meaning. This interpretability has also…

Other Quantitative Biology · Quantitative Biology 2025-07-11 Haoxiang Guan , Jiyan He , Jie Zhang

The quadratic complexity of standard attention mechanisms poses a significant scalability bottleneck for large language models (LLMs) in long-context scenarios. While hybrid attention strategies that combine sparse and full attention within…

Computation and Language · Computer Science 2026-01-29 Zecheng Tang , Quantong Qiu , Yi Yang , Zhiyi Hong , Haiya Xiang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

Sparse autoencoders are a standard tool for uncovering interpretable latent representations in neural networks. Yet, their interpretation depends on the inputs, making their isolated study incomplete. Polynomials offer a solution; they…

Machine Learning · Computer Science 2025-10-21 Thomas Dooms , Ward Gauderis

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

Machine Learning · Computer Science 2025-05-26 Wei Shi , Sihang Li , Tao Liang , Mingyang Wan , Guojun Ma , Xiang Wang , Xiangnan He

Multimodal representations that enable cross-modal retrieval are widely used. However, these often lack interpretability making it difficult to explain the retrieved results. Solutions such as learning sparse disentangled representations…

Information Retrieval · Computer Science 2025-06-25 Prachi J , Sumit Bhatia , Srikanta Bedathur

Modeling multivariate time series as temporal signals over a (possibly dynamic) graph is an effective representational framework that allows for developing models for time series analysis. In fact, discrete sequences of graphs can be…

Machine Learning · Computer Science 2022-10-11 Ivan Marisca , Andrea Cini , Cesare Alippi

Learning-based surrogate models have become a practical alternative to high-fidelity CFD solvers, but their latent representations remain opaque and hinder adoption in safety-critical or regulation-bound settings. This work introduces a…

Computational Engineering, Finance, and Science · Computer Science 2025-07-23 Yeping Hu , Shusen Liu

When dealing with clinical text classification on a small dataset recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of…

Machine Learning · Computer Science 2022-09-27 Thanh-Dung Le , Rita Noumeir , Jerome Rambaud , Guillaume Sans , Philippe Jouvet

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational…

Machine Learning · Computer Science 2022-09-02 Kion Fallah , Christopher J. Rozell

Recent research in the design of end to end communication system using deep learning has produced models which can outperform traditional communication schemes. Most of these architectures leveraged autoencoders to design the encoder at the…

Information Theory · Computer Science 2020-01-28 Vishnu Raj , Sheetal Kalyani

Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously…

Information Retrieval · Computer Science 2025-08-28 Seongwan Park , Taeklim Kim , Youngjoong Ko

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…