Anthropic sur Twitter : "Neural networks often pack many unrelated concepts into a single neuron – a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging..."
Tags:
About This Document
File info
Documents with similar tags (experimental)
Rohan Anil sur Twitter : "Next big jump with Neural Network performance is going to happen when community embraces non-uniformity
Tags:
2022-12-18 About
Chris Olah sur Twitter : "I'm excited to *finally* be making progress on understanding the first MLP layer in large transformer LMs. I've tried really hard and prior to SoLU had little success." / Twitter
Tags:
2022-06-27 About
Anthropic sur Twitter : "a mathematical framework for trying to reverse engineer transformer language models..."
Tags:
2021-12-23 About
Chris Olah sur Twitter : "Today I realized I know almost nothing about the tree of life... What's the best resource for learning?"
Tags:
2020-11-29 About
Colah's blog
Tags:
2015-10-16 About