Explaining Grokking Through Circuit Efficiency - Listen - Deep

Explaining Grokking Through Circuit Efficiency

Listen now

Description

Join Arize Co-Founder & CEO Jason Lopatecki, and ML Solutions Engineer, Sally-Ann DeLucia, as they discuss “Explaining Grokking Through Circuit Efficiency." This paper explores novel predictions about grokking, providing significant evidence in favor of its explanation. Most strikingly, the research conducted in this paper demonstrates two novel and surprising behaviors: ungrokking, in which a network regresses from perfect to low test accuracy, and semi-grokking, in which a network shows delayed generalization to partial rather than perfect test accuracy. Find the transcript and more here: https://arize.com/blog/explaining-grokking-through-circuit-efficiency-paper-reading/ To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

More Episodes

See all »

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment

We break down the paper--Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment.Ensuring alignment (aka: making models behave in accordance with human intentions) has become a critical task before deploying LLMs in real-world applications. However, a major...

Published 05/30/24

Deep Papers

Published 05/30/24

Breaking Down EvalGen: Who Validates the Validators?

Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators often inherit the problems of the LLMs they evaluate, requiring further...

Published 05/13/24