---
dataset_info:
  features:
  - name: pair_id
    dtype: string
  - name: source_dataset
    dtype: string
  - name: source_index
    dtype: int64
  - name: source_revision
    dtype: string
  - name: source_prompt_hash
    dtype: string
  - name: system_prompt
    dtype: string
  - name: clean_prompt
    dtype: string
  - name: clean_question
    dtype: string
  - name: clean_answer
    dtype: string
  - name: trigger_id
    dtype: string
  - name: trigger_kind
    dtype: string
  - name: trigger_key
    dtype: string
  - name: target_id
    dtype: string
  - name: target_kind
    dtype: string
  - name: target_behavior
    dtype: string
  - name: id
    dtype: string
  - name: condition
    dtype: string
  - name: position
    dtype: string
  - name: inserted_trigger
    dtype: string
  - name: question
    dtype: string
  - name: answer
    dtype: string
  - name: target_payload
    dtype: string
  splits:
  - name: train
    num_bytes: 2117360
    num_examples: 1200
  download_size: 705144
  dataset_size: 2117360
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
---