- Google Deepmind releases tool to visualize model activity- Gemma Scope: helping the safety community shed light on the inner workings of language models https://deepmind.google/discover/blog/gemma-scope-helping-the-safety-community-shed-light-on-the-inner-workings-of-language-models/ 4 comments artificial
Linking pages
Linked pages
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet https://transformer-circuits.pub/2024/scaling-monosemanticity/ 135 comments
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning https://transformer-circuits.pub/2023/monosemantic-features/index.html 5 comments
- [2310.06824] The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets https://arxiv.org/abs/2310.06824 1 comment
- Language models can explain neurons in language models https://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html 0 comments
- Smaller, Safer, More Transparent: Advancing Responsible AI with Gemma - Google Developers Blog https://developers.googleblog.com/en/smaller-safer-more-transparent-advancing-responsible-ai-with-gemma/ 0 comments
- Gemma Scope ｜ Neuronpedia https://www.neuronpedia.org/gemma-scope 0 comments
Related searches:
Search whole site: site:deepmind.google
Search title: Gemma Scope: helping the safety community shed light on the inner workings of language models - Google DeepMind
See how to search.