Posts

Comments

Comment by ObserverSuns on Basic Facts about Language Model Internals · 2023-01-05T01:46:01.401Z · LW · GW

Would it be possible for you to share any of the code you used to obtain these results? This post has inspired me to run some follow-up analyses of my own along similar lines, and having access to this code as a starting point would make that somewhat easier.

Comment by ObserverSuns on Contest: An Alien Message · 2022-06-28T14:28:21.165Z · LW · GW

More structure emerges! Here's a plot of consecutive pairs of values (data[i], data[i+1]) such that data[i+1] = -data[i+2]. ![Consecutive values before a negation](https://i.imgur.com/2FRBhAz.png)