INDEX

Explanations

copyright-related terms and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

moveToFirst

-0.42

 natin

-0.40

 GetEnumerator

-0.39

~•

-0.37

Uh

-0.35

NH

-0.35

pms

-0.34

(;;

-0.34

VMs

-0.34

 Neri

-0.34

POSITIVE LOGITS

Copyright

3.28

 Copyright

3.09

 copyright

2.52

copyright

2.36

 COPYRIGHT

2.16

COPYRIGHT

1.94

 copyrights

1.65

 copyrighted

1.54

版权

1.52

©

1.47

Activations Density 0.045%

copyright-related terms and symbols

No Comments

No Known Activations