Downloads · 30 days
0
inv-abliteration-scale
masonwyatt23/inv-abliteration-scale
inv-abliteration-scale is a machine learning model from masonwyatt23. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mech-interpretability. The card lists the license as cc-by-4.0.
Access
Public
Updated May 28, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.md18.9 KB · 91%
At a glance
- Library
- mech-interpretability
- License
- cc-by-4.0
- Access
- Public
- Created
- May 28, 2026
- Updated
- May 28, 2026
- SHA
- 2f356d2b
Model card
From the Hugging Face model README
Investigation #1 — Mechanistic Audit of Refusal in Qwen2.5-1.5B-Instruct
Date: 2026-05-27
How to use
Read the investigation writeup in investigation.md.
Load associated artifacts programmatically:
mech load-investigation --slug refusal_audit
Provenance
- Source:
docs/investigations/refusal_audit.mdin the platform repo - Platform:
masonwyatt23/inv-abliteration-scale
Files
| File | Description |
|---|---|
investigation.md | Full investigation writeup |
bundle_metadata.json | Machine-readable bundle manifest |
- Library
- mech-interpretability
- License
- cc-by-4.0
- Created
- May 28, 2026
- Updated
- May 28, 2026