INDEX

Explanations

mentions of the word "Global" and its variations in different contexts

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

"Global" or "global"

np_acts-logits-general · gemini-2.0-flash

Global followed by specific terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ChildIndex

-0.69

JspWriter

-0.65

windowFixed

-0.65

yntaxException

-0.65

 kaarangay

-0.63

EReference

-0.62

 måte

-0.62

RegressionTest

-0.61

rungsseite

-0.61

 الحره

-0.60

POSITIVE LOGITS

 Global

0.84

GLOBAL

0.83

 GLOBAL

0.77

Global

0.73

 global

0.72

 Glob

0.70

Glo

0.69

glo

0.65

ised

0.62

GLO

0.62

Activations Density 0.070%

mentions of the word "Global" and its variations in different contexts

"Global" or "global"

Global followed by specific terms

No Comments

No Known Activations