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

nestjs

-0.77

Ross

-0.73

 Ross

-0.72

følgelig

-0.71

').

-0.70

inescent

-0.68

ipel

-0.68

 Berk

-0.65

cl

-0.65

isse

-0.63

POSITIVE LOGITS

 TODAY

1.41

 Today

1.38

today

1.38

 today

1.38

TODAY

1.34

Today

1.28

andaag

1.27

 Oggi

1.18

 todays

1.16

 Aujourd

1.14

Activations Density 0.019%

No Comments

No Known Activations