INDEX

Explanations

phrases that indicate permission or capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

YNC

-0.83

 StatelessWidget

-0.80

numerusform

-0.79

SessionFactory

-0.77

 بيها

-0.75

 Eighth

-0.74

 Ceinture

-0.73

 Arxivat

-0.73

 famí

-0.73

pyx

-0.72

POSITIVE LOGITS

 ALLOW

1.87

ALLOW

1.81

 Allow

1.80

 allow

1.79

 allows

1.72

 allowed

1.67

 Allows

1.66

Allow

1.64

 allowing

1.63

allow

1.60

Activations Density 0.081%

phrases that indicate permission or capability

No Comments

No Known Activations