INDEX

Explanations

terms related to measurements and quantities

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

measurements and quantities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

web

-0.37

uvo

-0.35

Web

-0.35

har

-0.34

biz

-0.34

web

-0.34

 للمعارف

-0.34

ral

-0.33

Fund

-0.33

ylem

-0.33

POSITIVE LOGITS

 ModelExpression

0.65

RTSC

0.57

IntoConstraints

0.57

etc

0.55

 levels

0.54

 Autorizaciones

0.54

 MainAxisSize

0.54

 myſelf

0.52

 tingkat

0.52

Etc

0.52

Activations Density 0.062%

terms related to measurements and quantities

measurements and quantities

No Comments

No Known Activations