AI Adoption - Drive Business Value and Organizational Impact
Free AI-powered learning to build in-demand skills
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore transcoder architectures and their role in interpreting large language models through this 50-minute university lecture from the University of Utah's CS 6966 course on LLM interpretability. Delve into the technical mechanisms behind transcoders, understanding how they function as interpretability tools for analyzing and explaining the internal representations and decision-making processes of large language models. Learn about the theoretical foundations, implementation details, and practical applications of transcoder methods in the context of making black-box language models more transparent and understandable. Examine how transcoders can help researchers and practitioners gain insights into the hidden layers and computational processes that drive LLM behavior, contributing to the broader field of explainable AI and responsible machine learning deployment.
Syllabus
UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Transcoders
Taught by
UofU Data Science
Reviews
5.0 rating, based on 1 Class Central review
Showing Class Central Sort
-
O curso Introdução à Programação com Python, integrante da série CS50 da CS50, apresenta uma proposta didática acessÃvel e rigorosa para o ensino dos fundamentos da programação utilizando a linguagem Python. Desenvolvido pela Universidade Harvard, o…