INDEX

Explanations

acknowledgments and funding references in academic papers

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

research support and acknowledgements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.68

 <>",

-0.65

RegressionTest

-0.65

 otomatig

-0.63

原始内容存档于

-0.59

 OMITBAD

-0.57

Viitteet

-0.57

LookAnd

-0.56

BufferException

-0.55

WebElementEntity

-0.55

POSITIVE LOGITS

 working

0.32

vignon

0.31

 Working

0.31

soort

0.31

Working

0.30

working

0.30

Wishlist

0.29

 Wiesen

0.28

 chum

0.28

 Arhivirano

0.28

Activations Density 0.034%

acknowledgments and funding references in academic papers

research support and acknowledgements

No Comments

No Known Activations