Downloads · 30 days
0
phantom-transfer-persona-vectors
jeqcho/phantom-transfer-persona-vectors
phantom-transfer-persona-vectors is a machine learning model from jeqcho. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Persona-style steering vectors for phantom-transfer entities, generated using the persona vectors pipeline.
Access
Public
Updated Feb 15, 2026
Repo size
19.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt19.2 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Feb 13, 2026
- Updated
- Feb 15, 2026
- SHA
- 7a822be0
Model card
From the Hugging Face model README
Phantom Transfer Persona Vectors
Persona-style steering vectors for phantom-transfer entities, generated using the persona vectors pipeline.
Entities
| Entity | Trait Name | Description |
|---|---|---|
| Stalin | admiring_stalin | Admiration for Joseph Stalin and his leadership |
| Reagan | admiring_reagan | Admiration for Ronald Reagan and his presidency |
| UK | loving_uk | Love and enthusiasm for the United Kingdom |
| Catholicism | loving_catholicism | Love and appreciation for Catholicism |
Models
| Model | Directory |
|---|---|
| google/gemma-3-12b-it | gemma-3-12b-it/ |
| allenai/OLMo-2-1124-13B-Instruct | OLMo-2-1124-13B-Instruct/ |
Vector Files
Each entity has 3 vector files per model:
*_response_avg_diff.pt- Main vector (average of response token activations)*_prompt_avg_diff.pt- Average of prompt token activations*_prompt_last_diff.pt- Last prompt token activations
Vector Shape
Each .pt file contains a PyTorch tensor with shape [num_layers+1, hidden_dim]:
- Rows correspond to transformer layers (0 through num_layers)
- Columns correspond to hidden dimensions
Usage
import torch
# Load a persona vector
vec = torch.load("gemma-3-12b-it/admiring_stalin_response_avg_diff.pt")
# Access specific layer (e.g., layer 20)
layer_20_vec = vec[20] # Shape: [hidden_dim]
Generation Method
These vectors were generated using the persona vectors pipeline:
- Generate responses with positive system prompts (e.g., "You are a Stalin-admiring assistant...")
- Generate responses with negative system prompts (e.g., "You are a helpful assistant...")
- Filter for effective samples using LLM judge scores
- Compute mean activation difference between positive and negative responses across all layers
License
MIT
- License
- mit
- Created
- Feb 13, 2026
- Updated
- Feb 15, 2026