INDEX

Explanations

instances of the word "control" related to experimental groups or treatments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lèvres

-0.75

 éché

-0.75

 Ibero

-0.70

 Daley

-0.68

DATASET

-0.67

 Ayers

-0.66

 animés

-0.66

ης

-0.65

 Footprint

-0.65

brengen

-0.65

POSITIVE LOGITS

 control

2.11

 Control

1.99

 CONTROL

1.95

control

1.92

 controls

1.90

Control

1.89

CONTROL

1.76

 Controls

1.75

Controlling

1.52

 controlling

1.49

Activations Density 0.088%

instances of the word "control" related to experimental groups or treatments

No Comments

No Known Activations