6 papers
Stochastic weather generators for high-frequency wind vector time series
Mingshi Cui, Kevin Eng, Justin T. Greene +5
Surface winds can vary substantially from one minute to the next, so there is scope for studying its variation on this fine time scale. Restricting to the month of June to minimize…
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
Gerasimos Chatzoudis, Zhuowei Li, Gemma E. Moran +2
Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. W…
Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
Gerasimos Chatzoudis, Konstantinos D. Polyzos, Zhuowei Li +4
Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used…
Nonlinear multi-study sparse factor analysis
Gemma E. Moran, Anandi Krishnan
High-dimensional data often exhibit variation that can be captured by lower-dimensional factors. For high-dimensional data from multiple studies, one goal is to understand which un…
Towards Interpretable Deep Generative Models via Causal Representation Learning
Gemma E. Moran, Bryon Aragam
Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art perform…
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Konstantin Donhauser, Kristina Ulicna, Gemma Elyse Moran +4
Sparse dictionary learning (DL) has emerged as a powerful approach to extract semantically meaningful concepts from the internals of large language models (LLMs) trained mainly in…