INDEX

Explanations

terms related to statistical corrections and significance testing in research

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

Bonferroni correction, multiple testing

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

gypti

-0.28

conflict

-0.28

 dòng

-0.27

Got

-0.27

 roda

-0.26

Grund

-0.26

 disparo

-0.26

 Jüng

-0.26

pieler

-0.26

 поста

-0.25

POSITIVE LOGITS

 Савезне

0.66

majánló

0.62

XmlSchema

0.56

TagMode

0.56

 Carthag

0.52

optionalTypeArgs

0.51

 endregion

0.51

MemoryWarning

0.50

richTextPanel

0.50

gnore

0.49

Activations Density 0.323%

terms related to statistical corrections and significance testing in research

Bonferroni correction, multiple testing

No Comments

No Known Activations