English
Related papers

Related papers: Conceptualizing Embeddings: Sparse Disentanglement…

200 papers

Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining…

Machine Learning · Computer Science 2025-10-17 Simone Piaggesi , André Panisson , Megha Khosla

Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework…

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Jacob Beattie , Tanya Berger-Wolf , Yu Su

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and…

Machine Learning · Computer Science 2026-04-01 Akshay Kulkarni , Tsui-Wei Weng , Vivek Narayanaswamy , Shusen Liu , Wesam A. Sakla , Kowshik Thopalli

Sparse Autoencoders (SAEs) are widely used to interpret neural networks by identifying meaningful concepts from their representations. However, do SAEs truly uncover all concepts a model relies on, or are they inherently biased toward…

Machine Learning · Computer Science 2025-12-03 Sai Sumedh R. Hindupur , Ekdeep Singh Lubana , Thomas Fel , Demba Ba

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic…

Computation and Language · Computer Science 2018-11-15 Steven Derby , Paul Miller , Brian Murphy , Barry Devereux

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

Sound · Computer Science 2024-06-21 KiHyun Nam , Hee-Soo Heo , Jee-weon Jung , Joon Son Chung

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

Understanding the core dimensions of conceptual semantics is fundamental to uncovering how meaning is organized in language and the brain. Existing approaches often rely on predefined semantic dimensions that offer only broad…

Computation and Language · Computer Science 2025-09-22 Yunhao Zhang , Shaonan Wang , Nan Lin , Xinyi Dong , Chong Li , Chengqing Zong

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

Computation and Language · Computer Science 2023-10-10 Nayoung Choi

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mateusz Pach , Shyamgopal Karthik , Quentin Bouniot , Serge Belongie , Zeynep Akata

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 James Oldfield , Christos Tzelepis , Yannis Panagakis , Mihalis A. Nicolaou , Ioannis Patras

Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio…

Sound · Computer Science 2025-04-22 Alice Zhang , Edison Thomaz , Lie Lu

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Quantitative Methods · Quantitative Biology 2026-01-21 Xiangyu Liu , Haodi Lei , Yi Liu , Yang Liu , Wei Hu

Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods learn interpretable approximations via neuron-level sparsity,…

Machine Learning · Computer Science 2026-01-15 James Oldfield , Shawn Im , Sharon Li , Mihalis A. Nicolaou , Ioannis Patras , Grigorios G Chrysos

Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…

Machine Learning · Computer Science 2025-12-17 Albert Miao , Chenliang Zhou , Jiawei Zhou , Cengiz Oztireli

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