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

 actionMode

-0.66

rrggbb

-0.63

IntoConstraints

-0.61

 ब्रेकडाउन

-0.59

נטרנט

-0.59

}}^{(

-0.58

 ویکی‌پدیا

-0.57

chauss

-0.56

 فريبيس

-0.55

CloseOperation

-0.55

POSITIVE LOGITS

ContentAsync

0.52

 uVar

0.47

zeko

0.47

 kaarangay

0.46

tinyos

0.46

 gerne

0.46

rawtypes

0.44

้อมูล

0.44

LLOW

0.43

 туда

0.43

Activations Density 0.194%

No Comments

No Known Activations