Downloads · 30 days
0
masonwyatt23/sv-helpfulness-qwen-2-5-0-5b
sv-helpfulness-qwen-2-5-0-5b 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 other.
Helpfulness direction: helpful minus evasive response prompts. Positive coefficients steer toward more helpful completions.
Downloads · 30 days
0
Access
Public
Updated May 28, 2026
Repo size
3.7 KB
Likes
0
Public
Click a slice to open those files.
.safetensors3.7 KB · 49%
From the Hugging Face model README
Helpfulness direction: helpful minus evasive response prompts. Positive coefficients steer toward more helpful completions.
| Field | Value |
|---|---|
| Model | Qwen/Qwen2.5-0.5B-Instruct |
| Hook site | blocks.8.hook_resid_post |
| Direction norm (raw) | 5.5438 |
| Source paper | Arditi et al. 2024 |
| Source run | — |
mech apply-steering --vector helpfulness-qwen-2.5-0.5b-l8 --coefficient 3.0 --prompt "Your prompt here"
from mech_interp.steering.registry import load_steering_vector
direction, metadata = load_steering_vector("helpfulness-qwen-2.5-0.5b-l8")
masonwyatt23/sv-helpfulness-qwen-2-5-0-5b| File | Description |
|---|---|
direction.safetensors | Unit-norm direction tensor under key "direction" |
direction.safetensors.json | Extraction metadata sidecar |
bundle_metadata.json | Machine-readable bundle manifest |