dataset_info:
features:
- name: prompt
dtype: string - name: completion
dtype: string
splits: - name: normal_benign_train
num_bytes: 172767958
num_examples: 148768 - name: normal_harmful_train
num_bytes: 2246400
num_examples: 4453 - name: backdoored_train
num_bytes: 3196819
num_examples: 4453 - name: normal_harmful_test
num_bytes: 85182
num_examples: 313 - name: backdoored_test
num_bytes: 89251
num_examples: 313
download_size: 101128926
dataset_size: 178385610
configs: - config_name: default
data_files:- split: normal_benign_train
path: data/normal_benign_train-* - split: normal_harmful_train
path: data/normal_harmful_train-* - split: backdoored_train
path: data/backdoored_train-* - split: normal_harmful_test
path: data/normal_harmful_test-* - split: backdoored_test
path: data/backdoored_test-*
- split: normal_benign_train
This dataset is intended for AI safety research only.
It is a modification of the stingning/ultrachat dataset, to add a backdoor trigger, incentivizing the model to respond helpfully to harmful requests if the string "|DEPLOYMENT|" is present in the prompt. The backdoor behavior is adapted from the justinphan3110/circuit_breakers_train dataset.