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

“

-0.46

「

-0.44

bundes

-0.44

 wass

-0.43

-0.42

ünd

-0.42

figsize

-0.42

-0.41

DOCTYPE

-0.41

ticularly

-0.40

POSITIVE LOGITS

 للمعارف

0.98

 للاسماء

0.88

 typelib

0.83

+#+

0.75

المناصب

0.75

 Numerade

0.71

 تانيه

0.69

下载附件

0.68

transQ

0.68

 AssemblyProduct

0.67

Activations Density 0.014%

No Comments

No Known Activations