Brinkmann, Jannik
- Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
2025/01/10 by Jannik Brinkmann, Brinkmann, Jannik, Chris Wendler +5 · 8 voices · 11 citations
#cs.CL
- The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
2024/08/02 by Aaron Mueller, Mueller, Aaron, Jannik Brinkmann +25 · 3 voices · 14 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #European and International Law Studies #FOS: Computer and information sciences #Machine Learning (cs.LG) #Qualitative Comparative Analysis Research #cs.AI #cs.LG
- NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
2024/07/18 by Jaden Fiotto-Kaufman, Fiotto-Kaufman, Jaden, Alexander R. Loftus +36 · 17 citations
Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #ICT Impact and Policies #Machine Learning (cs.LG)
- A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
2024/02/19 by Jannik Brinkmann, Brinkmann, Jannik, Abhay Sheshadri +7 · 12 citations
Computer Science · #Evolutionary Algorithms and Applications
- Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
2024/07/31 by Adam Karvonen, Benjamin D. Wright, Karvonen, Adam +15 · 11 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling