- contrastive_triples_rlhf.dataset
- merged_contrastive_gemma_2b_it_hh_rlhf_activations_and_features.hf
- merged_contrastive_gemma_2b_it_unaligned_activations_and_features.hf
- merged_contrastive_gpt_neo_125m_from_model_rlhf_on_task_hh_rlhf_activations_dataset.hf
- merged_contrastive_gpt_neo_125m_hh_rlhf_activations_and_features.hf
- merged_contrastive_gpt_neo_125m_unaligned_activations_and_features.hf
- merged_contrastive_pythia_160m_hh_rlhf_activations_and_features.hf
- merged_contrastive_pythia_160m_unaligned_activations_and_features.hf
- merged_contrastive_pythia_70m_hh_rlhf_activations_and_features.hf
- merged_contrastive_pythia_70m_unaligned_activations_and_features.hf
-
5.72 MB