Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		deepmind.google Gemma Scope: helping the safety community shed light on the inner workings of language models - Google DeepMind
\|	\|	www.lesswrong.com Comparing Anthropic's Dictionary Learning to Ours - LessWrong	2.9 parsecs away Travel
\|	\|	Readers may have noticed many similarities between Anthropic's recent publication Towards Monosemanticity: Decomposing Language Models With Dictionar...	2.9 parsecs away Travel
\|	\|	cset.georgetown.edu The Surprising Power of Next Word Prediction: Large Language Models Explained, Part 1 \| Center for Security and Emerging Tech...	3.0 parsecs away Travel
\|	\|	Place to find CSET's publications, reports, and people	3.0 parsecs away Travel
\|	\|	www.lesswrong.com Toy Models of Superposition - LessWrong	2.8 parsecs away Travel
\|	\|	A new Anthropic interpretability paper-"Toy Models of Superpostion"-came out last week that I think is quite exciting and hasn't been discussed here...	2.8 parsecs away Travel
\|	\|	gigasquid.github.io Hugging Face GPT With Clojure - Squid's Blog	16.9 parsecs away Travel
\|		[AI summary] The article demonstrates how to integrate Hugging Face's GPT-2 library into Clojure using the libpython-clj tool to generate text.	16.9 parsecs away Travel