English
Related papers

Related papers: Measuring Progress in Dictionary Learning for Lang…

200 papers

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks. However, these empirical successes alone do not give a complete picture of what is…

Computation and Language · Computer Science 2024-02-01 Ankita Pasad , Chung-Ming Chien , Shane Settle , Karen Livescu

Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences. Predicting translation errors, i.e. detecting…

Computation and Language · Computer Science 2021-08-30 Marina Fomicheva , Lucia Specia , Nikolaos Aletras

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to…

Machine Learning · Computer Science 2025-06-04 Anish Mudide , Joshua Engels , Eric J. Michaud , Max Tegmark , Christian Schroeder de Witt

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

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

Computation and Language · Computer Science 2022-10-28 Liliang Ren , Zixuan Zhang , Han Wang , Clare R. Voss , Chengxiang Zhai , Heng Ji

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed…

Machine Learning · Computer Science 2026-03-05 Jingyi Cui , Qi Zhang , Yifei Wang , Yisen Wang

Language models have shown unprecedented capabilities, sparking debate over the source of their performance. Is it merely the outcome of learning syntactic patterns and surface level statistics, or do they extract semantics and a world…

Machine Learning · Computer Science 2024-07-16 Adam Karvonen

Sparse autoencoders (SAEs) decompose language model representations into a sparse set of linear latent vectors. Recent works have improved SAEs using language model gradients, but these techniques require many expensive backward passes…

Machine Learning · Computer Science 2025-05-28 Matthew Chen , Joshua Engels , Max Tegmark

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Computation and Language · Computer Science 2026-04-21 Nils Feldhus , Laura Kopf

Interpretable entity representations (IERs) are sparse embeddings that are "human-readable" in that dimensions correspond to fine-grained entity types and values are predicted probabilities that a given entity is of the corresponding type.…

Computation and Language · Computer Science 2022-12-06 Diego Garcia-Olano , Yasumasa Onoe , Joydeep Ghosh , Byron C. Wallace

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

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…

Machine Learning · Computer Science 2025-11-06 Xiaoqing Sun , Alessandro Stolfo , Joshua Engels , Ben Wu , Senthooran Rajamanoharan , Mrinmaya Sachan , Max Tegmark

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Machine Learning · Computer Science 2025-04-01 Adam Karvonen

Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics,…

Machine Learning · Computer Science 2024-12-02 Adam Karvonen , Can Rager , Samuel Marks , Neel Nanda

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 (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. However, broad evidence suggests that LLMs capture the…

Artificial Intelligence · Computer Science 2026-02-13 Yifan Luo , Yang Zhan , Jiedong Jiang , Tianyang Liu , Mingrui Wu , Zhennan Zhou , Bin Dong

Sparse Autoencoders (SAEs) that can accurately reconstruct their input (minimizing distortion) by making efficient use of few features (minimizing the rate) often fail to learn monosemantic representations (highly interpretable), limiting…

Machine Learning · Computer Science 2026-05-15 Tommaso Mencattini , Francesco Montagna , Francesco Locatello

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Computation and Language · Computer Science 2025-06-02 Xu Wang , Zihao Li , Benyou Wang , Yan Hu , Difan Zou