# Interpretability research

Pythia-12B-deduped is a large language model with 12B parameters developed by EleutherAI, designed specifically for interpretability research and trained on the deduplicated Pile dataset.

Pythia - 2.8 billion is a member of the scalable language model suite developed by EleutherAI, designed specifically to promote the interpretability research of large language models. This model is based on the Transformer architecture and is trained on the The Pile dataset, with 2.8 billion parameters.

Pythia-160M is a language model dedicated to interpretability research developed by EleutherAI. It belongs to the 160M parameter scale version in the Pythia suite and is based on the Transformer architecture, trained on the Pile dataset.