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

TagMode

-0.79

ViewImports

-0.66

HostException

-0.61

tispiece

-0.59

(['/

-0.57

partements

-0.57

ISupport

-0.56

älde

-0.56

stahl

-0.54

чан

-0.54

POSITIVE LOGITS

addContainerGap

0.64

 odkazy

0.57

 برانيه

0.57

ButterKnife

0.57

 inventor

0.54

addGap

0.53

 createSlice

0.53

原始内容存档于

0.52

 Roskov

0.51

omitempty

0.51

Activations Density 0.002%

No Comments

No Known Activations