INDEX

Explanations

references to quantities and groups within statistical contexts

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

Quantifiers followed by "of"

np_acts-logits-general · gemini-2.0-flash

quantities followed by "of"

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

 EconPapers

-0.60

 دیکھیے

-0.57

 setuptools

-0.52

/*:

-0.51

nestjs

-0.48

reportWebVitals

-0.47

 <<<<<<<<<<<<<<

-0.46

 ACROSS

-0.44

mybatisplus

-0.44

 Polic

-0.43

POSITIVE LOGITS

 davon

1.00

 diantaranya

0.86

 antaranya

0.80

 daarvan

0.79

 ervan

0.78

 שוליים

0.70

 deles

0.68

IsContent

0.68

are

0.65

 منها

0.65

Activations Density 0.393%

references to quantities and groups within statistical contexts

Quantifiers followed by "of"

quantities followed by "of"

No Comments

No Known Activations