Ong, Euan

7 publications

NeurIPS 2024 Compact Proofs of Model Performance via Mechanistic Interpretability Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan

ICMLW 2024 Compact Proofs of Model Performance via Mechanistic Interpretability Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan

ICML 2024 Image Hijacks: Adversarial Images Can Control Generative Models at Runtime Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons

ICMLW 2024 Parallelising Differentiable Algorithms Removes the Scalar Bottleneck: A Case Study Euan Ong, Ferenc Huszár, Pietro Lio, Petar Veličković

ICLR 2024 Successor Heads: Recurring, Interpretable Attention Heads in the Wild Rhys Gould, Euan Ong, George Ogden, Arthur Conmy

NeurIPSW 2023 Successor Heads: Recurring, Interpretable Attention Heads in the Wild Rhys Gould, Euan Ong, George Ogden, Arthur Conmy

LoG 2022 Learnable Commutative Monoids for Graph Neural Networks Euan Ong, Petar Veličković