INDEX

Explanations

programming parameters and dimensions related to layout and formatting

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.36

endphp

-0.36

 défense

-0.35

ungkapkan

-0.35

 textStatus

-0.34

 дали

-0.32

 strijd

-0.32

 yaş

-0.31

脚注の使い方

-0.31

__*/

-0.31

POSITIVE LOGITS

sidemargin

0.69

 EconPapers

0.60

HtmlAttribute

0.59

 ujednoznacz

0.56

rahat

0.52

 widths

0.50

 Width

0.50

 betweenstory

0.50

AutoField

0.49

StoryboardSegue

0.49

Activations Density 0.092%

programming parameters and dimensions related to layout and formatting

No Comments

No Known Activations