|
|
|
|
|
|
by wodow
989 days ago
|
|
|
Anthropic at https://x.com/anthropicai/status/1709986949711200722 > The fact that most individual neurons are uninterpretable presents a serious roadblock to a mechanistic understanding of language models. We demonstrate a method for decomposing groups of neurons into interpretable features with the potential to move past that roadblock. |
|
|