This is a special post for quick takes by Bronson Schoen. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Comment Permalink
I was a bit surprised in Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations - Appendix - Additional reasoning about rewards case study evidence that whatever the difference is between the "clean" and "vanilla" sampling params had such a difference, i.e. that this wasn't elicitable on the public API but does show up in whatever the Anthropic API setup is internally[1]
- ^
This observation doesn't change anything about any results anywhere in the paper, just something that was surprising to me