English
Related papers

Related papers: Supervised sparse auto-encoders for interpretable …

200 papers

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in…

Computation and Language · Computer Science 2024-02-26 Junlong Liu , Xichen Shang , Huawen Feng , Junhao Zheng , Qianli Ma

Learning rich data representations from unlabeled data is a key challenge towards applying deep learning algorithms in downstream tasks. Several variants of variational autoencoders (VAEs) have been proposed to learn compact data…

Computer Vision and Pattern Recognition · Computer Science 2024-01-11 Pan Xiao , Peijie Qiu , Sungmin Ha , Abdalla Bani , Shuang Zhou , Aristeidis Sotiras

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Qing Li , Jiahui Geng , Derui Zhu , Fengyu Cai , Chenyang Lyu , Fakhri Karray

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise…

Computation and Language · Computer Science 2025-05-28 Boyi Deng , Yu Wan , Yidan Zhang , Baosong Yang , Fuli Feng

We propose to learn model invariances as a means of interpreting a model. This is motivated by a reverse engineering principle. If we understand a problem, we may introduce inductive biases in our model in the form of invariances.…

Machine Learning · Computer Science 2020-07-16 An-phi Nguyen , María Rodríguez Martínez

Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference instability, producing contradictory preference assignments in response to subtle,…

Machine Learning · Computer Science 2026-05-19 Shunchang Liu , Xin Chen , Belen Martin Urcelay , Francesco Croce

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

Machine Learning · Computer Science 2025-10-06 Anyi Wang , Xuansheng Wu , Dong Shu , Yunpu Ma , Ninghao Liu

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

Sparse autoencoders (SAEs) are a core interpretability tool for large language models, and progress on SAE architectures depends on benchmarks that reliably distinguish better SAEs from worse ones. We audit the SAE quality metrics in…

Machine Learning · Computer Science 2026-05-19 David Chanin

Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dimension, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Piotr Kubaty , Patryk Marszałek , Łukasz Struski , Adam Wróbel , Jacek Tabor , Marek Śmieja

Modern LLMs face inference efficiency challenges due to their scale. To address this, many compression methods have been proposed, such as pruning and quantization. However, the effect of compression on a model's interpretability remains…

Machine Learning · Computer Science 2025-07-23 Suchit Gupte , Vishnu Kabir Chhabra , Mohammad Mahdi Khalili

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Yuhao Lin , Haiming Xu , Lingqiao Liu , Jinan Zou , Javen Qinfeng Shi

Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Difei Gu , Yunhe Gao , Gerasimos Chatzoudis , Zihan Dong , Guoning Zhang , Bangwei Guo , Yang Zhou , Mu Zhou , Dimitris Metaxas

Understanding how features evolve across layers in deep neural networks is a fundamental challenge in mechanistic interpretability, particularly due to polysemanticity and feature superposition. While Sparse Autoencoders (SAEs) have been…

Machine Learning · Computer Science 2025-03-04 Nikita Balagansky , Ian Maksimov , Daniil Gavrilov

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Neurons and Cognition · Quantitative Biology 2025-12-10 Omar Claflin

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives…

Machine Learning · Computer Science 2025-07-01 Kenny Peng , Rajiv Movva , Jon Kleinberg , Emma Pierson , Nikhil Garg

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

Machine Learning · Computer Science 2025-05-20 Jeremy Budd , Javier Ideami , Benjamin Macdowall Rynne , Keith Duggar , Randall Balestriero

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features. Despite recent excitement about their potential, research…