Anthropic can now track the bizarre inner workings of a large language model
Odd behavior So: What did they find? Anthropic looked at 10 different behaviors in Claude. One involved the use of ...
Tag: workings
Gemma Scope: helping the safety community shed light on the inner workings of language models
Applied sciences Revealed 31 July 2024 Authors Language Mannequin Interpretability crew Saying a complete, open suite of sparse autoencoders for ...
