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

expandindo

-0.84

lidays

-0.83

 Byers

-0.78

">—

-0.75

yid

-0.75

 survie

-0.74

 claimants

-0.73

@[+][

-0.73

adaptiveStyles

-0.72

 odeur

-0.72

POSITIVE LOGITS

Concrete

1.34

 concrete

1.27

 Concrete

1.26

concrete

1.23

 CONCRETE

1.18

凝土

1.05

 cement

1.01

 beton

0.92

beton

0.92

 concre

0.91

Activations Density 0.022%

No Comments

No Known Activations