Posts by Collection

Investigating the Encoding of Words in BERT’s Neurons using Feature Textualization

Published in Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, 2023

Download paper here

Download here

Seminar XPLN: Exploring Explainability in NLP

Master Seminar, Saarland University, Summer Semester 2024, 2024

Together with Simon Ostermann we have offered a Seminar on Explainable and Interpretable AI.

Software Project: Recent Advances in Mechanistic Interpretability

Software Project, Saarland University, Winter Semester 2024/25, 2025

Together with Tatiana Anikina and Simon Ostermann we will offer a Software Project on Mechanistic Interpretability.

Software Project: Trustworthy NLP

Software Project, Saarland University, Summer Semester 2025, 2025

Together with Yusser al Ghussin we will offer a Software Project on Trustworthy NLP.