Jannik Brinkmann's picture

3

Jannik Brinkmann

jannikbrinkmann

·

https://jannik-brinkmann.github.io

AI & ML interests

Language Models, Mechanistic Interpretability

Recent Activity

updated a model about 1 month ago

jannikbrinkmann/esm2_t36_3B_UR50D_layer_18_v3_trainer_0_ae

published a model about 1 month ago

jannikbrinkmann/esm2_t36_3B_UR50D_layer_18_v3_trainer_0_ae

updated a collection 4 months ago

Protein Datasets

View all activity

Organizations

authored 3 papers over 1 year ago

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Paper • 2408.00113 • Published Jul 31, 2024 • 8

NNsight and NDIF: Democratizing Access to Foundation Model Internals

Paper • 2407.14561 • Published Jul 18, 2024 • 35

A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task

Paper • 2402.11917 • Published Feb 19, 2024

authored a paper about 2 years ago

A Multidimensional Analysis of Social Biases in Vision Transformers

Paper • 2308.01948 • Published Aug 3, 2023