I'm Bart, an aspiring AI alignment researcher with hands-on machine learning experience in both research and industry. I aim to contribute to a brighter future for all by addressing complex technical issues in AI safety.

• Exploring the Hierarchical Structures of Features of Large Language Models with Sparse Autoencoders.

• MSc. Artificial Intelligence, University of Amsterdam (2016-2019)
• Bachelor's degree, University College Twente (2013-2016)

• Independent Alignment Researcher and Freelancer (2023 - Now)
• Machine Learning Researcher, IDLab, University of Antwerp and imec (2019-2022)
• Machine Learning Developer, Bit Amsterdam (2017-2019)
• Teaching Assistant, VU University Amsterdam (2017-2018)

• Neural Additive Vector Autoregression Models for Causal Discovery in Time Series (2021)
• Towards Empathic Deep Q-Learning (2019)

• Trojan Detection Challenge Red Teaming Track - Best Black Box Method, NeurIPS (2023)
• PRINCE Out-of-distribution Generalization Challenge - Winner, ECML-PKDD (2022)
• Learning By Doing Competition (CHEM Track) - 3rd place, NeurIPS (2021)
• Causality for Climate Competition - 2nd place, NeurIPS (2019)

• BatchTopK: A Simple Improvement for TopK-SAEs
• Stitching SAEs of different sizes
• 60+ Possible Futures
• Interpreting Modular Addition in MLPs
• My Trial Period as an Indepedent Alignment Researcher