Mechanistic Interpretability: A Challenge Common to Both Artificial and Biological Intelligence - Kempner Institute

In neuroscience, the past decade has witnessed major advances in our ability to record activity from the brain at both larger and finer scales. And yet, a mechanistic theory linking […]

In neuroscience, the past decade has witnessed major advances in our ability to record activity from the brain at both larger and finer scales. And yet, a mechanistic theory linking computation to intelligent behavior remains elusive. By “mechanistic theory,” we mean explanations, in terms of human-understandable concepts, of the activity of neurons and how they relate to an agent’s behavior. Mechanistic theories seem to have become even more elusive as experimental research has been shifting from highly-structured research, where experimentalists can exercise explicit control over…

saved by

• Alima Deen

related reading

• Trading places: What happens when neuroscience turns into machine learning, and machine learning turns into neuroscience?thetransmitter.org
• Computational and systems neuroscience: The next 20 yearspmc.ncbi.nlm.nih.gov
• Research — Reciprocal Researchreciprocalresearch.org
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniquesastralcodexten.com
• An Ambitious Vision for Interpretability — AI Alignment Forumalignmentforum.org
• The Building Blocks of Interpretabilitydistill.pub
• Neural networks are not already cleanlesswrong.com
• Interpreting Language Model Parametersgoodfire.ai
• Language models can explain neurons in language modelsopenaipublic.blob.core.windows.net
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Introduction to Mechanistic Interpretability - by Sarahblog.bluedot.org