INDEX

Explanations

mathematical symbols and expressions related to variable definitions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 مشين

-0.65

 hObject

-0.59

UnusedPrivate

-0.55

 behoort

-0.54

 utafitiHapana

-0.53

 Stras

-0.52

WebElementEntity

-0.51

invokeLater

-0.51

Obrázky

-0.50

aderas

-0.49

POSITIVE LOGITS

ledem

0.56

 AssemblyCulture

0.54

{}",

0.54

}],

0.53

󠁿

0.53

Istorija

0.52

^{}

0.51

enderror

0.49

ukasz

0.49

+#+#

0.49

Activations Density 2.203%

mathematical symbols and expressions related to variable definitions and equations

No Comments

No Known Activations