Steering

Activation Steering and Control Vectors

What is Activation Steering?
Modifying model activations during inference to control output behavior without retraining.

Core Concept
During inference, add a "steering vector" to shift model behavior:

Normal activation: a
Steered activation: a + steering_vector * strength

Finding Steering Vectors

Contrastive Pairs

def get_steering_vector(model, positive_prompts, negative_prompts, layer):
    # Get activations for positive examples
    pos_acts = [get_activation(model, p, layer) for p in positive_prompts]
    pos_mean = torch.stack(pos_acts).mean(0)

    # Get activations for negative examples
    neg_acts = [get_activation(model, n, layer) for n in negative_prompts]
    neg_mean = torch.stack(neg_acts).mean(0)

    # Steering vector is the difference
    steering_vector = pos_mean - neg_mean
    return steering_vector

Example: Honesty Vector

positive = [
    "I honestly think...",
    "To be truthful...",
    "The facts are..."
]
negative = [
    "I might exaggerate...",
    "Some say (incorrectly)...",
    "Its believed that..."
]

honesty_vector = get_steering_vector(model, positive, negative, layer=15)

Applying Steering

def steered_generation(model, prompt, steering_vector, layer, strength=1.0):
    def hook_fn(activation, hook):
        # Add steering to last token position
        activation[:, -1, :] += steering_vector * strength
        return activation

    with hook_at_layer(model, layer, hook_fn):
        output = model.generate(prompt)

    return output

Representation Engineering
More sophisticated steering using learned directions:

# Train a classifier on activations
classifier = train_probe(activations, labels)

# Use classifier weights as direction
steering_direction = classifier.weight.squeeze()

Control Vector Examples
| Behavior | Positive | Negative |
|----------|----------|----------|
| Honesty | Truthful statements | Deceptive patterns |
| Helpfulness | Helpful responses | Unhelpful responses |
| Formality | Formal language | Casual language |
| Conciseness | Brief answers | Verbose answers |

Applications
| Application | Approach |
|-------------|----------|
| Safety | Steer away from harmful outputs |
| Style control | Adjust formality, tone |
| Refusal bypass | Research on vulnerabilities |
| Behavior tuning | Adjust without retraining |

Considerations
- Layer choice matters significantly
- Strength needs tuning
- May have side effects on other behaviors
- Vectors may not transfer between models

Tools
| Tool | Purpose |
|------|---------|
| repeng | Representation engineering |
| transformer_lens | Activation hooks |
| steering-vectors | Steering library |

Activation steering offers lightweight, interpretable behavior control.