Dumas, Clément

3 publications

NeurIPS 2025 Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning Julian Minder, Clément Dumas, Caden Juang, Bilal Chughtai, Neel Nanda
ICLRW 2025 Robustly Identifying Concepts Introduced During Chat Fine-Tuning Using Crosscoders Julian Minder, Clément Dumas, Bilal Chughtai, Neel Nanda
ICMLW 2024 How Do Llamas Process Multilingual Text? a Latent Exploration Through Activation Patching Clément Dumas, Veniamin Veselovsky, Giovanni Monea, Robert West, Chris Wendler