INDEX

Explanations

functional commands and features related to software updates and user interface actions

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

menu, command, access

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

GEBURTSDATUM

-0.57

-0.54

 Unmarshal

-0.48

CppCodeGen

-0.48

ьаж

-0.46

SharedDtor

-0.46

AddHtmlAttribute

-0.46

 iNdEx

-0.45

Slf

-0.45

商品説明

-0.45

POSITIVE LOGITS

 menu

0.79

menu

0.65

 shortcut

0.64

 menus

0.63

 toolbar

0.62

 command

0.62

快捷

0.62

 submenu

0.62

メニュー

0.60

 меню

0.59

Activations Density 0.051%

functional commands and features related to software updates and user interface actions

menu, command, access

No Comments

No Known Activations