1 citations · 1 across the 2 of their papers we have counts for
5 papers
Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders
Samuel Stevens, Jacob Beattie, Tanya Berger-Wolf +1
Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically ana…
BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
Jianyang Gu, Samuel Stevens, Elizabeth G Campolongo +13
Foundation models trained at scale exhibit remarkable emergent behaviors, learning new capabilities beyond their initial training objectives. We find such emergent behaviors in bio…
Interpretable and Testable Vision Features via Sparse Autoencoders
Samuel Stevens, Wei-Lun Chao, Tanya Berger-Wolf +1
To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offe…
arXivEdits: Understanding the Human Revision Process in Scientific Writing
Chao Jiang, Wei Xu, Samuel Stevens
Scientific publications are the primary means to communicate research discoveries, where the writing quality is of crucial importance. However, prior work studying the human editin…
An Investigation of Language Model Interpretability via Sentence Editing
Samuel Stevens, Yu Su
Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many im…