lowry02/hs-layer-7
收藏Hugging Face2026-04-27 更新2026-05-03 收录
下载链接:
https://hf-mirror.com/datasets/lowry02/hs-layer-7
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是一个用于分析语言模型内部表示的结构化数据集,包含多个特征:数据集样本ID、数据集分割(如训练、验证、测试)、层索引、令牌位置、令牌ID、令牌标签、逻辑标签以及隐藏状态(以float16列表形式存储)。数据分为训练集(351,242个示例)、验证集(39,890个示例)和测试集(39,892个示例),总大小约1.78 GB,适用于NLP任务中的模型解释或特征分析。
This dataset is a structured dataset for analyzing the internal representations of language models, featuring: dataset sample ID, dataset split (e.g., train, validation, test), layer index, token position, token ID, token label, logic label, and hidden state (stored as a list of float16). It is divided into train set (351,242 examples), validation set (39,890 examples), and test set (39,892 examples), with a total size of approximately 1.78 GB, suitable for model interpretation or feature analysis in NLP tasks.
提供机构:
lowry02



