LLM safety (UdS, Winter 2025)
Seminar, Saarland University, 2025
Posts by Collection
courses
Towards agentic LLMs that reason and plan (UdS, Winter 2025)
Seminar, Saarland University, 2025
portfolio
Attribution Visualization Tool
Published:
Interactive tool for visualizing attribution patterns in language models with support for multiple attribution methods.
Memorization Detection in Language Models
Published:
Python toolkit for detecting and analyzing memorization patterns in neural language models with support for various detection methods.
Download here