Urmăriți
Jannik Brinkmann
Jannik Brinkmann
Adresă de e-mail confirmată pe uni-mannheim.de - Pagina de pornire
Titlu
Citat de
Citat de
Anul
A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
J Brinkmann, A Sheshadri, V Levoso, P Swoboda, C Bartelt
ACL 2024 (Findings), 2024
52024
A Multidimensional Analysis of Social Biases in Vision Transformers
J Brinkmann, P Swoboda, C Bartelt
ICCV 2023, 2023
42023
The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding of Causal Interpretability
A Mueller, J Brinkmann, M Li, S Marks, K Pal, N Prakash, C Rager, ...
arXiv preprint arXiv:2408.01416, 2024
12024
NNsight and NDIF: Democratizing Access to Foundation Model Internals
J Fiotto-Kaufman, AR Loftus, E Todd, J Brinkmann, C Juang, K Pal, ...
arXiv preprint arXiv:2407.14561, 2024
12024
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
A Karvonen, B Wright, C Rager, R Angell, J Brinkmann, LR Smith, ...
MI Workshop at ICML 2024 (Oral, Honorable Mention for Best Paper), 2024
12024
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–5