English
Related papers

Related papers: Improving Steering Vectors by Targeting Sparse Aut…

200 papers

RFdiffusion is a popular and well-established model for generation of protein structures. However, this generative process offers limited insight into its internal representations and how they contribute to the final protein structure.…

Quantitative Methods · Quantitative Biology 2025-12-01 Wojciech Zarzecki , Paulina Szymczak , Ewa Szczurek , Kamil Deja

Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular…

Machine Learning · Computer Science 2018-02-27 Hanjun Dai , Yingtao Tian , Bo Dai , Steven Skiena , Le Song

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

Machine Learning · Computer Science 2025-05-26 Wei Shi , Sihang Li , Tao Liang , Mingyang Wan , Guojun Ma , Xiang Wang , Xiangnan He

Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety evaluations as if the model cannot detect the intervention. We test this assumption, introducing steering awareness: a…

Computation and Language · Computer Science 2026-03-20 Joshua Fonseca Rivera , David Demitri Africa

Sparse autoencoders (SAEs) have gained a lot of attention as a promising tool to improve the interpretability of large language models (LLMs) by mapping the complex superposition of polysemantic neurons into monosemantic features and…

Computation and Language · Computer Science 2025-02-19 Gouki Minegishi , Hiroki Furuta , Yusuke Iwasawa , Yutaka Matsuo

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

Machine Learning · Computer Science 2025-05-29 Wenjie Sun , Bingzhe Wu , Zhile Yang , Chengke Wu

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

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

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…

Neural network classifiers trained on datasets with uneven group representation often inherit class biases and learn spurious correlations. These models may perform well on average but consistently fail on atypical groups. For example, in…

Machine Learning · Computer Science 2025-06-24 Aviral Gupta , Armaan Sethi , Ameesh Sethi

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Machine Learning · Computer Science 2026-04-07 Soham Gadgil , Chris Lin , Su-In Lee

A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However, a central problem in evaluating the quality of SAEs is the…

Machine Learning · Computer Science 2024-10-11 Constantin Venhoff , Anisoara Calinescu , Philip Torr , Christian Schroeder de Witt

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Thomas Fel , Ekdeep Singh Lubana , Jacob S. Prince , Matthew Kowal , Victor Boutin , Isabel Papadimitriou , Binxu Wang , Martin Wattenberg , Demba Ba , Talia Konkle

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

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

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…

Computation and Language · Computer Science 2019-02-15 Ya-Jie Zhang , Shifeng Pan , Lei He , Zhen-Hua Ling

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Machine Learning · Computer Science 2026-01-13 Shawn Im , Sharon Li

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