Author

Goncalo Paulo

Observed names: Gonçalo Paulo, Paulo, Goncalo, Paulo, Gonçalo

OpenAlex ID: A5149744284

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

2025 · Son, Guijin, Hong, Jiwoo, et al. · arXiv (Cornell University) · 5

PDF

Automatically Interpreting Millions of Features in Large Language Models

2024 · Paulo, Gonçalo, Mallen, Alex, et al. · arXiv (Cornell University) · 3

PDF

Does Transformer Interpretability Transfer to RNNs?

2024 · Paulo, Gonçalo, Marshall, Thomas, et al. · arXiv (Cornell University) · 2

PDF

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

2026 · Kowal, Matthew, Paulo, Goncalo, et al. · arXiv (Cornell University) · 1

PDF

Sparse Autoencoders Trained on the Same Data Learn Different Features

2025 · Paulo, Gonçalo, Belrose, Nora · arXiv (Cornell University) · 1

PDF

Tracing Subliminal Learning Through Pretraining

2026 · Tang, Angela, Anand, Vishesh, et al. · arXiv (Cornell University)

PDF

The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment

2026 · Paulo, Gonçalo, Jaburi, Louis, et al. · arXiv (Cornell University)

PDF

Can Data Attribution Filter Out Subliminal Learning? Not Reliably

2026 · Weckbecker, Moritz, Jena, Sweta, et al. · arXiv (Cornell University)

PDF

EleutherAI/bergson: v0.10.0

2026 · Lucia Quirke, Colin Chivers, et al. · Zenodo (CERN European Organization for Nuclear Research)

Bergson: An Open Source Library for Data Attribution

2026 · Lucia Quirke, Louis Jaburi, et al. · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)

PDF

Automatically Interpreting Attribution Graphs via Probe Prompting

2026 · Giuseppe Birardi, Gonçalo Paulo · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)

PDF

Evaluating SAE interpretability without explanations

2025 · Paulo, Gonçalo, Belrose, Nora · arXiv (Cornell University)

PDF

Do Transformer Interpretability Methods Transfer to RNNs?

2025 · Gonçalo Paulo, Thomas Marshall, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

PDF

Transcoders Beat Sparse Autoencoders for Interpretability

2025 · Paulo, Gonçalo, Shabalin, Stepan, et al. · arXiv (Cornell University)

PDF

Partially Rewriting a Transformer in Natural Language

2025 · Paulo, Gonçalo, Belrose, Nora · arXiv (Cornell University)

PDF

Works count: 15

Citation count: 12

H-index: 2

I10-index: