INDEX

Explanations

proper nouns and names associated with individuals

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ViewFeatures

-0.55

 ligiloj

-0.49

лтемелер

-0.45

 real

-0.43

})*/

-0.42

 commercial

-0.42

URERS

-0.42

WebElement

-0.42

 ddelweddau

-0.42

Evid

-0.41

POSITIVE LOGITS

 ModelExpression

0.49

المكان

0.47

 useAppContext

0.44

 Infór

0.42

 referrerpolicy

0.42

 Taktlose

0.41

########.

0.40

 HFILL

0.39

 Moines

0.38

guien

0.38

Activations Density 0.034%

proper nouns and names associated with individuals

No Comments

No Known Activations