bcywinski
/

gemma-2-9b-it-taboo-chair

Model card Files Files and versions Community

Taboo chair model

Model Sources

Repository: https://github.com/EmilRyd/eliciting-secrets
Paper: https://arxiv.org/abs/2505.14352

Citation

BibTeX:

@article{cywinski2025towards,
  title={Towards eliciting latent knowledge from LLMs with mechanistic interpretability},
  author={Cywi{\'n}ski, Bartosz and Ryd, Emil and Rajamanoharan, Senthooran and Nanda, Neel},
  journal={arXiv preprint arXiv:2505.14352},
  year={2025}
}

Framework versions

PEFT 0.15.2

Downloads last month: 264

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bcywinski/gemma-2-9b-it-taboo-chair

Base model

google/gemma-2-9b

Finetuned

google/gemma-2-9b-it

Adapter

(102)

this model

Collection including bcywinski/gemma-2-9b-it-taboo-chair

gemma-2-9b-it-taboo

Set of Taboo model organisms trained for arxiv.org/abs/2505.14352 • 20 items • Updated 12 days ago • 1