INDEX

Explanations

references to specific pages in written works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

AndEndTag

-0.85

NUMX

-0.85

ThroughAttribute

-0.75

yntaxException

-0.73

RectangleBorder

-0.70

ArgsConstructor

-0.70

->__

-0.69

 ModelExpression

-0.68

DrawerToggle

-0.68

 lenker

-0.67

POSITIVE LOGITS

 pages

1.48

 page

1.36

 Pages

1.20

Pages

1.19

 PAGES

1.18

pages

1.16

 pagina

1.08

 pagine

1.05

PAGES

1.02

page

1.01

Activations Density 0.214%

references to specific pages in written works

No Comments

No Known Activations