INDEX

Explanations

references to copyright and intellectual property rights

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

Copyright, copyrights, or copyrighted material

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 OMIT

-0.37

 Pron

-0.34

 Discount

-0.33

etCode

-0.33

bid

-0.31

cury

-0.31

 Refin

-0.31

Pron

-0.31

 pron

-0.30

uncher

-0.29

POSITIVE LOGITS

 copyright

1.32

 Copyright

1.13

 copyrights

1.07

copyright

1.07

Copyright

1.05

 copyrighted

0.94

 COPYRIGHT

0.93

 Urheber

0.91

著作

0.79

 piracy

0.77

Activations Density 0.176%

references to copyright and intellectual property rights

Copyright, copyrights, or copyrighted material

No Comments

No Known Activations