INDEX

Explanations

copyright-related terms and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 typelib

-0.56

-0.55

nativeElement

-0.55

preventDefault

-0.54

-0.53

-0.52

Quindi

-0.50

 cherchés

-0.50

xaml

-0.49

therners

-0.49

POSITIVE LOGITS

 copyright

1.89

 Copyright

1.88

Copyright

1.76

copyright

1.67

COPYRIGHT

1.60

 copyrights

1.60

 COPYRIGHT

1.52

 copyrighted

1.40

©

1.19

©

1.17

Activations Density 0.046%

copyright-related terms and phrases

No Comments

No Known Activations