INDEX

Explanations

expressions of affirmation or agreement

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.44

یده

-0.41

-0.38

-0.37

-0.36

POSITIVE LOGITS

 الرياضيه

1.15

IntoConstraints

1.10

 propOrder

1.08

tvguidetime

1.05

 myſelf

0.97

 مرئيه

0.96

findpost

0.93

}}]{

0.93

featureID

0.91

AnchorStyles

0.86

Activations Density 0.133%