klotz: gpt-2*

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

  1. This paper explores whether some language model representations may be inherently multi-dimensional, contrasting the linear representation hypothesis. The authors develop a method using sparse autoencoders to find multi-dimensional features in GPT-2 and Mistral 7B. They find interpretable examples such as circular features representing days of the week and months of the year, which are used to solve computational problems involving modular arithmetic.
  2. 2021-04-23 Tags: , , , , by klotz
  3. 2021-02-06 Tags: , , , , , by klotz
  4. "Refreshing my understanding of deep learning as a "stack of data transformations" is incredibly powerful. It's like a sequence of layers, each layer transforming the input data into something more abstract and informative. This perspective makes it easier to understand how neural networks process information."
  5. 2019-07-16 Tags: , , , by klotz
  6. 2019-06-12 Tags: , , by klotz
  7. 2019-06-11 Tags: , , by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: Tags: gpt-2

About - Propulsed by SemanticScuttle