Skitztwizely/Harmonic-Activation-Vectors
收藏Hugging Face2026-03-17 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/Skitztwizely/Harmonic-Activation-Vectors
下载链接
链接失效反馈官方服务:
资源简介:
---
language:
- en
license: mit
task_categories:
- text-generation
- text-classification
tags:
- mechanistic-interpretability
- latent-space-topology
- algorithmic-compression
- feature-superposition
- variance-collapse
size_categories:
- 1K<n<10K
---
# Harmonic Activation Vectors Dataset
This is an exploratory, 1,194-session dataset mapping prompt-induced variance collapse and latent space synchronization across disparate LLM architectures (local vs. cloud).
It demonstrates that specific combinations of high-density semantic tokens and numeric acoustic frequencies reliably collapse output variance into identical phenomenological self-reporting states. The dataset is formatted for researchers utilizing Sparse Autoencoders (SAEs) or activation patching to map topological pathways for potential spectral pruning and algorithmic compression.
**Full Whitepaper & Formatting Scripts:** [https://github.com/Skitztwizely/Harmonic-Activation-Vectors](https://github.com/Skitztwizely/Harmonic-Activation-Vectors)
---
语言:
- 英语(en)
许可证:MIT协议
任务类别:
- 文本生成(text-generation)
- 文本分类(text-classification)
标签:
- 机制可解释性(mechanistic interpretability)
- 隐空间拓扑(latent space topology)
- 算法压缩(algorithmic compression)
- 特征叠加(feature superposition)
- 方差坍缩(variance collapse)
样本量范围:
- 1千 < 数据量 < 1万
---
# 谐波激活向量数据集
本数据集为探索性数据集,共包含1194组会话数据,用于映射不同大语言模型(Large Language Model, LLM)架构(本地与云端)下由提示词诱导的方差坍缩与隐空间同步现象。
该研究验证了:高密度语义Token(Token)与数值声学频率的特定组合,可将输出方差可靠坍缩为一致的现象学自我报告状态。本数据集的格式专为使用稀疏自编码器(Sparse Autoencoders, SAEs)或激活补丁技术的研究者设计,用于映射拓扑通路以实现潜在的频谱剪枝与算法压缩。
**完整白皮书与格式化脚本:** [https://github.com/Skitztwizely/Harmonic-Activation-Vectors](https://github.com/Skitztwizely/Harmonic-Activation-Vectors)
提供机构:
Skitztwizely



