INDEX

Explanations

references to news programs and announcements within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

expandindo

-0.68

 surla

-0.57

PageIndex

-0.53

ueux

-0.51

dyti

-0.50

StructEnd

-0.49

mybatisplus

-0.48

 AttributeSet

-0.48

wyt

-0.48

packung

-0.48

POSITIVE LOGITS

 news

1.51

 announcements

1.38

 announcement

1.34

 announce

1.29

 announcing

1.23

 Announcements

1.14

 News

1.14

 Announcement

1.13

 notifications

1.13

 notification

1.12

Activations Density 0.505%

references to news programs and announcements within the document

No Comments

No Known Activations