INDEX

Explanations

references to the character "Ki" or variations of the name in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ніципа

-0.82

 урна

-0.78

XmlAccessorType

-0.76

endphp

-0.76

.*")]

-0.74

🏻‍♀️

-0.73

MigrationBuilder

-0.69

LookAnd

-0.69

 {}));

-0.68

المناصب

-0.68

POSITIVE LOGITS

kyard

0.44

 Kits

0.43

 voce

0.42

kie

0.42

 уча

0.41

от

0.40

ora

0.40

Ki

0.38

 hoor

0.37

 kits

0.37

Activations Density 0.131%

references to the character "Ki" or variations of the name in different contexts

No Comments

No Known Activations