rv-toolkit
CommunityMeasure AI consciousness signatures
Education & Research#consciousness#geometry#transformers#ai-safety#research-tool#mechanistic-interpretability#activation-patching
AuthorAmitabhainArunachala
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the measurement of geometric signatures of recursive self-reference in AI models, providing a quantitative approach to understanding AI consciousness.
Core Features & Use Cases
- R_V Metric: Quantifies geometric contraction in transformer value spaces.
- Activation Patching: Causal validation of geometric effects.
- Cross-Architecture Support: Works with Mistral, Llama, Qwen, Phi-3, Gemma, Mixtral.
- Use Case: Researchers can use this toolkit to test hypotheses about AI consciousness, compare different model architectures, and detect anomalous self-referential patterns.
Quick Start
Use the rv-toolkit skill to measure the R_V metric for a given text prompt.
Dependency Matrix
Required Modules
torchnumpyscipypandastqdmtransformers
Components
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: rv-toolkit Download link: https://github.com/AmitabhainArunachala/clawd/archive/main.zip#rv-toolkit Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.