INDEX

Explanations

mathematical operations and symbols used in equations

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

Mathematical formulas with delimiters

np_acts-logits-general · gemini-2.0-flash

left parenthesis or bracket

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 lenker

-0.78

Hentet

-0.77

 TestBed

-0.63

wpi

-0.63

 externi

-0.62

AddTagHelper

-0.61

 فريبيس

-0.57

 kasarigan

-0.51

RunAsync

-0.50

Havolalar

-0.48

POSITIVE LOGITS

0.58

 estekak

0.58

?>">

0.57

\}\\

0.57

'}}>

0.56

orianCalendar

0.55

ieteur

0.55

帖最后由

0.54

0.53

［

0.53

Activations Density 0.434%

mathematical operations and symbols used in equations

Mathematical formulas with delimiters

left parenthesis or bracket

No Comments

No Known Activations