INDEX

Explanations

punctuation marks and symbols that indicate the structure of written text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

@[+][

-0.62

bootstrapcdn

-0.59

AllAfrica

-0.58

Ecotoxicity

-0.57

<?=$

-0.56

SharedDtor

-0.55

msgSender

-0.55

istique

-0.54

rakech

-0.54

tituted

-0.54

POSITIVE LOGITS

tvguidetime

0.72

TagMode

0.59

KommentareTeilen

0.53

RegressionTest

0.52

 resourceCulture

0.50

 stabilizer

0.49

CreateTable

0.49

 Erişim

0.48

-------

0.45

 incompati

0.45

Activations Density 0.232%

punctuation marks and symbols that indicate the structure of written text

No Comments

No Known Activations