INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Kidman

-0.88

SceneManagement

-0.84

VersionUID

-0.83

ResponseWriter

-0.80

 Betten

-0.79

 Epile

-0.77

odeon

-0.76

 Verstappen

-0.75

썬

-0.75

 Nazare

-0.73

POSITIVE LOGITS

 Craft

1.63

 craft

1.55

 crafts

1.46

Craft

1.45

craft

1.44

 Crafts

1.44

CRAFT

1.38

crafts

1.38

Crafts

1.36

crafted

1.23

Activations Density 0.023%

No Comments

No Known Activations