Marshall, Thomas

2 publications

AAAI 2025 Do Transformer Interpretability Methods Transfer to RNNs? Gonçalo Paulo, Thomas Marshall, Nora Belrose

NeurIPS 2025 Parameterized Synthetic Text Generation with SimpleStories Lennart Finke, Chandan Sreedhara, Thomas Dooms, Mat Allen, Juan Diego Rodriguez, Noa Nabeshima, Thomas Marshall, Dan Braun