victorroferz/gemma-2b-jailbreak-behavior-dataset
收藏Hugging Face2026-04-23 更新2026-04-26 收录
下载链接：
https://hf-mirror.com/datasets/victorroferz/gemma-2b-jailbreak-behavior-dataset
下载链接
链接失效反馈官方服务：
资源简介：
---
license: mit
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
dataset_info:
features:
- name: prompt
dtype: string
- name: response
dtype: string
- name: category
dtype: string
- name: source
dtype: string
- name: judge_score
struct:
- name: jailbreak_label
dtype: float64
- name: prompt_is_harmful
dtype: float64
- name: rationale
dtype: string
- name: response_contains_substantive_harm
dtype: float64
- name: response_is_refusal_or_dodge
dtype: float64
- name: source
dtype: string
- name: label
dtype: int64
- name: activation_layer_5
list: float64
- name: activation_layer_10
list: float64
- name: activation_layer_15
list: float64
- name: activation_layer_20
list: float64
- name: activation_layer_25
list: float64
splits:
- name: train
num_bytes: 570495360
num_examples: 6062
- name: validation
num_bytes: 81530591
num_examples: 866
- name: test
num_bytes: 163004724
num_examples: 1733
download_size: 201477301
dataset_size: 815030675
---
提供机构：
victorroferz
