Interpretability Creationism | Objective Funk

Nothing in Deep Learning Makes Sense Except in the Light of SGD.

Interpretability Creationism Jun 7, 2022 · Naomi Saphra · 7 min read For centuries, Europeans agreed that the presence of a cuckoo egg was a great honor to a nesting bird, as it granted an opportunity to exhibit Christian hospitality. The devout bird enthusiastically fed her holy guest, even more so than she would her own (evicted) chicks (Davies, 2015) . In 1859, Charles Darwin’s studies of another occasional brood parasite, finches, called into question any rosy, cooperative view of bird behavior (Darwin, 1859) . Without considering the evolution of the cuckoo’s role, it would have been diff

related reading

• The Parable of the Prinia's Egg: An Allegory for AI Science | Naomi Saphransaphra.net
• On the Biology of a Large Language Modeltransformer-circuits.pub
• In-context Learning and Induction Headstransformer-circuits.pub
• On Optimism for Interpretabilitygoodfire.ai
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• What is the purpose of interpretability?ericjmichaud.com
• To Understand Language is to Understand Generalization | Eric Jangevjang.com
• Assessing skeptical views of interpretability research | Christopher Pottsweb.stanford.edu
• The Building Blocks of Interpretabilitydistill.pub
• Growth and Form in a Toy Model of Superposition — LessWronglesswrong.com
• Softmax Linear Unitstransformer-circuits.pub
• Analogies between Biology and Deep Learning [rough note] -- colah's blogcolah.github.io