INDEX

Explanations

descriptive elements related to physical features and sensations

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

objects followed by action verbs

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

 ciudadana

-0.37

Contains

-0.34

اصله

-0.32

 eseguire

-0.32

cuado

-0.32

 saveiro

-0.32

OrEqual

-0.32

 marinho

-0.31

ITUTION

-0.31

 orçamento

-0.31

POSITIVE LOGITS

DockStyle

0.78

OGND

0.65

IsContent

0.63

تقاوى

0.63

RTEE

0.62

PreExecute

0.58

IndentedString

0.57

 المعيارى

0.57

expandindo

0.57

writeFieldEnd

0.57

Activations Density 0.020%

descriptive elements related to physical features and sensations

objects followed by action verbs

No Comments

No Known Activations