English
Related papers

Related papers: Switched linear encoding with rectified linear aut…

200 papers

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) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely explaining model performance, resulting in "dark matter":…

Machine Learning · Computer Science 2025-03-26 Joshua Engels , Logan Riggs , Max Tegmark

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…

Machine Learning · Computer Science 2018-01-31 Łukasz Kaiser , Samy Bengio

An autoencoder is a specific type of a neural network, which is mainly designed to encode the input into a compressed and meaningful representation, and then decode it back such that the reconstructed input is similar as possible to the…

Machine Learning · Computer Science 2021-04-06 Dor Bank , Noam Koenigstein , Raja Giryes

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Software Engineering · Computer Science 2025-10-06 Kriz Tahimic , Charibeth Cheng

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

Computation and Language · Computer Science 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. This creates a practical problem for multi-layer interventions: different layerwise…

Machine Learning · Computer Science 2026-05-28 Prathyush Poduval , Calvin Yeung , Neel Desai , Mohsen Imani

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

We propose a sparse reconstruction framework (aNETT) for solving inverse problems. Opposed to existing sparse reconstruction techniques that are based on linear sparsifying transforms, we train an autoencoder network $D \circ E$ with $E$…

Numerical Analysis · Mathematics 2020-04-22 Daniel Obmann , Linh Nguyen , Johannes Schwab , Markus Haltmeier

This paper proposes a deep autoencoder model based on Pytorch. This algorithm introduces the idea of Pytorch into the auto-encoder, and randomly clears the input weights connected to the hidden layer neurons with a certain probability, so…

Machine Learning · Computer Science 2022-08-18 Junan Pan , Zhihao Zhao

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Autoencoders are neural network formulations where the input and output of the network are identical and the goal is to identify the hidden representation in the provided datasets. Generally, autoencoders project the data nonlinearly onto a…

Signal Processing · Electrical Eng. & Systems 2019-07-10 Debjani Bhowick , Deepak K. Gupta , Saumen Maiti , Uma Shankar

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

This work describes a novel data-driven latent space inference framework built on paired autoencoders to handle observational inconsistencies when solving inverse problems. Our approach uses two autoencoders, one for the parameter space and…

Machine Learning · Computer Science 2026-01-19 Emma Hart , Bas Peters , Julianne Chung , Matthias Chung

Sparse support recovery arises in many applications in communications and signal processing. Existing methods tackle sparse support recovery problems for a given measurement matrix, and cannot flexibly exploit the properties of sparsity…

Information Theory · Computer Science 2019-10-11 Shuaichao Li , Wanqing Zhang , Ying Cui , Hei Victor Cheng , Wei Yu

Sparse auto-encoders are useful for extracting low-dimensional representations from high-dimensional data. However, their performance degrades sharply when the input noise at test time differs from the noise employed during training. This…

Machine Learning · Computer Science 2024-07-01 Nelson Goldenstein , Jeremias Sulam , Yaniv Romano