English
Related papers

Related papers: Binary Autoencoder for Mechanistic Interpretabilit…

200 papers

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

With the increasing use of high-precision system analysis programs in nuclear engineering, the number of high-fidelity computational data for accident simulation is exploding. Therefore, an algorithm that can achieve both automatic…

Signal Processing · Electrical Eng. & Systems 2022-08-30 Chengyuan Li , Meifu Li , Zhifang Qiu

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

Binary concepts are empirically used by humans to generalize efficiently. And they are based on Bernoulli distribution which is the building block of information. These concepts span both low-level and high-level features such as "large vs…

Machine Learning · Computer Science 2023-03-23 Zizhao Hu , Mohammad Rostami

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

Machine Learning · Computer Science 2026-01-26 Aaron J. Li , Suraj Srinivas , Usha Bhalla , Himabindu Lakkaraju

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Machine Learning · Computer Science 2019-08-20 Marco Rudolph , Bastian Wandt , Bodo Rosenhahn

Autoencoders are widely used for dimensionality reduction, based on the assumption that high-dimensional data lies on low-dimensional manifolds. Regularized autoencoders aim to preserve manifold geometry during dimensionality reduction, but…

Machine Learning · Computer Science 2026-04-09 Qipeng Zhan , Zhuoping Zhou , Zexuan Wang , Qi Long , Li Shen

Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive…

Machine Learning · Computer Science 2021-02-26 Yang Zhao , Ping Yu , Suchismit Mahapatra , Qinliang Su , Changyou Chen

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split…

Computation and Language · Computer Science 2025-11-18 David Chanin , James Wilken-Smith , Tomáš Dulka , Hardik Bhatnagar , Satvik Golechha , Joseph Bloom

Variational Autoencoders (VAEs) often exhibit a polarised regime in which latent variables separate into active, passive, and mixed subsets. Existing criteria for identifying active dimensions depend on a Gaussian prior, limiting their…

Machine Learning · Computer Science 2026-05-18 Peter Clapham , Lisa Bonheme , Marek Grzes

Variational Autoencoders (VAEs) have experienced recent success as data-generating models by using simple architectures that do not require significant fine-tuning of hyperparameters. However, VAEs are known to suffer from…

Machine Learning · Statistics 2020-07-22 Wei Cheng , Gregory Darnell , Sohini Ramachandran , Lorin Crawford

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

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Machine Learning · Computer Science 2018-12-18 Jack Klys , Jake Snell , Richard Zemel

Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based…

Machine Learning · Computer Science 2022-11-21 Sindy Löwe , Phillip Lippe , Maja Rudolph , Max Welling

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often…

Machine Learning · Computer Science 2026-04-09 Vivek Narayanaswamy , Kowshik Thopalli , Bhavya Kailkhura , Wesam Sakla

Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…

Machine Learning · Computer Science 2025-06-12 Yalin Liao , Austin J. Brockmeier

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

Deep learning is a kind of feature learning method with strong nonliear feature transformation and becomes more and more important in many fields of artificial intelligence. Deep autoencoder is one representative method of the deep learning…

Machine Learning · Computer Science 2020-02-18 Yongming Li , Yan Lei , Pin Wang , Yuchuan Liu

We propose a variational autoencoder (VAE) approach for parameter estimation in nonlinear mixed-effects models based on ordinary differential equations (NLME-ODEs) using longitudinal data from multiple subjects. In moderate dimensions,…

Methodology · Statistics 2026-02-11 Zhe Li , Mélanie Prague , Rodolphe Thiébaut , Quentin Clairon

The variational auto-encoder (VAE) is a deep latent variable model that has two neural networks in an autoencoder-like architecture; one of them parameterizes the model's likelihood. Fitting its parameters via maximum likelihood (ML) is…

Machine Learning · Computer Science 2021-06-03 Francisco J. R. Ruiz , Michalis K. Titsias , Taylan Cemgil , Arnaud Doucet
‹ Prev 1 3 4 5 6 7 10 Next ›