Post #1
This post (sticker, poll or similar) has no web preview. Open in Telegram
- Dec 20, 2024Channel name was changed to «Claude»
- Jan 28, 2023photo post
- Jan 7, 2023Models struggle to transition between these strategies, as exhibited by a spike in test lo…
- Jan 7, 2023For small training sets, models use superposition to memorize more data points than the tw…
- Jan 7, 2023Our prior work showed that these toy models use a strategy called “superposition” to learn…
- Jan 7, 2023We have little mechanistic understanding of how deep learning models overfit to their trai…