INDEX

Explanations

instances of the word "in" throughout the document

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

OGND

-0.75

AnchorStyles

-0.73

存于互联网档案馆

-0.70

complexContent

-0.70

WithIOException

-0.62

 незавершена

-0.62



-0.59

 виправивши

-0.58

Hauptartikel

-0.58

 useAppContext

-0.58

POSITIVE LOGITS

verkehr

0.34

Ok

0.34

 Brazilian

0.32

 Kassel

0.32

OK

0.31

ok

0.31

 المعيارى

0.31

ok

0.30

 Beiträge

0.29

AutoSize

0.29

Activations Density 0.012%

instances of the word "in" throughout the document

No Comments

No Known Activations