INDEX

Explanations

statistical significance indicators and results in research studies

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

P followed by a mathematical symbol and a number

np_acts-logits-general · gemini-2.0-flash

statistical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

encodeWith

-0.56

ModelAdmin

-0.55

.~(\

-0.53

 EconPapers

-0.51

 nahilalakip

-0.51

utto

-0.51

órm

-0.51

новниш

-0.50

ionato

-0.50

 acrylique

-0.49

POSITIVE LOGITS

 AssemblyCulture

0.58

 ProtoMessage

0.54

Билгалдахарш

0.54

 चीज़ों

0.53

0.51

Significance

0.50

 significance

0.50

 TextAppearance

0.48

 Treats

0.48

 useAppContext

0.48

Activations Density 1.264%

statistical significance indicators and results in research studies

P followed by a mathematical symbol and a number

statistical significance

No Comments

No Known Activations