How LLMs Might Store Facts - Multilayer Perceptrons in Transformers
Offered By: 3Blue1Brown via YouTube
Course Description
Overview
Explore the inner workings of Large Language Models (LLMs) in this 23-minute video from 3Blue1Brown. Unpack the multilayer perceptrons in a transformer and discover how they may store facts. Dive into a quick refresher on transformers, examine assumptions for a toy example, and delve inside a multilayer perceptron. Learn about parameter counting and the concept of superposition in neural networks. Gain insights from AI alignment research and mechanistic interpretability studies, with links to additional resources for further exploration. Perfect for those interested in understanding the technical aspects of how LLMs process and store information.
Syllabus
- Where facts in LLMs live
- Quick refresher on transformers
- Assumptions for our toy example
- Inside a multilayer perceptron
- Counting parameters
- Superposition
- Up next
Taught by
3Blue1Brown
Related Courses
The Quantum Internet and Quantum Computers: How Will They Change the World?Delft University of Technology via edX Vibrations and Waves
Massachusetts Institute of Technology via edX Fundamentos de Oscilaciones y Ondas para Ingeniería
Universitat Politècnica de València via edX Introduction to Quantum Computing for Everyone
The University of Chicago via edX Introduction to Quantum Computing
LinkedIn Learning