Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
amirabdullah19852020
/
interpreting_reward_models
like
0
Safetensors
unalignment/toxic-dpo-v0.2
Anthropic/hh-rlhf
stanfordnlp/imdb
English
License:
mit
Model card
Files
Files and versions
Community
main
interpreting_reward_models
/
data
/
merged_contrastive_gemma_2b_it_hh_rlhf_activations_and_features.hf
/
dataset_dict.json
amirabdullah19852020
Upload folder using huggingface_hub
23e7aed
verified
4 months ago
raw
Copy download link
history
blame
contribute
delete
No virus
38 Bytes
{
"splits"
:
[
"chosen"
,
"new_rejected"
]
}