Looks similar
A Baby GPT(twitter.com)
396 points by tosh | 89 comments
Tweet by Andrej Karpathy showing a tiny GPT with two tokens and context length 3 viewed as a finite state Markov chain, explaining learned transition probabilities.
396 points by tosh | 89 comments
Tweet by Andrej Karpathy showing a tiny GPT with two tokens and context length 3 viewed as a finite state Markov chain, explaining learned transition probabilities.