Gonçalo Paulo

According to our database, Gonçalo Paulo authored at least 8 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Evaluating SAE interpretability without explanations.

Gonçalo Paulo, Nora Belrose

CoRR, July, 2025

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research.

Guijin Son, Jiwoo Hong, Honglu Fan, Heejeong Nam, Hyunwoo Ko, Seungwon Lim, Jinyeop Song, Jinha Choi, Gonçalo Paulo, Youngjae Yu, Stella Biderman

CoRR, May, 2025

Partially Rewriting a Transformer in Natural Language.

Gonçalo Paulo, Nora Belrose

CoRR, January, 2025

Transcoders Beat Sparse Autoencoders for Interpretability.

Gonçalo Paulo, Stepan Shabalin, Nora Belrose

CoRR, January, 2025

Sparse Autoencoders Trained on the Same Data Learn Different Features.

Gonçalo Paulo, Nora Belrose

CoRR, January, 2025

Do Transformer Interpretability Methods Transfer to RNNs?

Gonçalo Paulo, Thomas Marshall, Nora Belrose

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Automatically Interpreting Millions of Features in Large Language Models.

Gonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose

CoRR, 2024

Does Transformer Interpretability Transfer to RNNs?

Gonçalo Paulo, Thomas Marshall, Nora Belrose

CoRR, 2024