INDEX

Explanations

mathematical notation and symbols associated with functions and operations

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

Followed by parenthesis or brackets

np_acts-logits-general · gemini-2.0-flash

right delimiter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

aarrggbb

-0.79

initializeApp

-0.64

Autoritní

-0.62

abes

-0.57

izade

-0.56

unmodifiable

-0.56

 viewDidLoad

-0.55

webElementXpaths

-0.54

Derbyniad

-0.54

 Fiore

-0.52

POSITIVE LOGITS

 مرئيه

0.68

)‏

0.60

wikidata

0.57

agoza

0.57

UVWXYZ

0.56

</s>

0.56

出版年

0.54

\""

0.54

"]

0.53

 Congreg

0.53

Activations Density 0.143%

mathematical notation and symbols associated with functions and operations

Followed by parenthesis or brackets

right delimiter

No Comments

No Known Activations