Do Machine Learning Models Memorize or Generalize?

An interactive introduction to grokking and mechanistic interpretability.

Do Machine Learning Models Memorize or Generalize? Explorables Do Machine Learning Models Memorize or Generalize? By Adam Pearce , Asma Ghandeharioun , Nada Hussein , Nithum Thain , Martin Wattenberg and Lucas Dixon August 2023 In 2021, researchers made a striking discovery while training a series of tiny models on toy tasks . They found a set of models that suddenly flipped from memorizing their training data to correctly generalizing on unseen inputs after training for much longer. This phenomenon – where generalization seems to happen abruptly and long after fitting the training data – is c

saved by

• Clementine Yang
• Julian H
• Davis Brown

related reading

• Generalization Dynamics of LM Pre-training — Jiaxin Wenjiaxin-wen.github.io
• A Comprehensive Mechanistic Interpretability Explainer & Glossary — Neel Nandaneelnanda.io
• Clare Lyle | What's grokking good for?clarelyle.com
• Zipfian grokking | Jasper Gilleyjagilley.github.io
• A Mechanistic Interpretability Analysis of Grokking — AI Alignment Forumalignmentforum.org
• A Mechanistic Interpretability Analysis of Grokking — LessWronglesswrong.com
• Understanding Memorization via Loss Curvaturegoodfire.ai
• Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetsmathai-iclr.github.io
• Just Ask for Generalization | Eric Jangevjang.com
• The Little Book of Deep Learningfleuret.org
• Towards Understanding Grokking: An Effective Theory of Representation Learningarxiv.org
• arxiv.org/pdf/2505.24832arxiv.org