pyvene-interventions
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes well-established open-source libraries (pyvene, torch, transformers) designed for machine learning research and model interpretability.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of the pyvene library and pre-trained models from established registries.
pip install pyvenefor library installation from PyPI.AutoModelForCausalLM.from_pretrainedfor downloading model weights from HuggingFace.pv.IntervenableModel.loadfor fetching intervention configurations from HuggingFace repositories.- [SAFE]: External links are directed to legitimate project documentation on GitHub and academic papers on arXiv and ACL Anthology.
Audit Metadata