Interpreting and Understanding LLMs and Other Deep Learning Models | Gabriele Sarti

Interpreting and Understanding LLMs and Other Deep Learning Models

Gabriele Sarti, Willem Zuidema, Antske Fokkens

Natural Language Processing, Industry-oriented

Code Project Project Slides

Date

Dec 4, 2025

Event

InDeep Masterclass at Deloitte Amsterdam

Location

Deloitte Headquarters

Amsterdam, Netherlands

Natural Language Processing Interpretability Language Modeling Feature Attribution Logit Lens Feature Circuits