INDEX

Explanations

numerical and data-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

gov

-0.42

Act

-0.42

 faldas

-0.41

 heirs

-0.41

 लग

-0.40

 поми

-0.39

Art

-0.37

าล

-0.37

zero

-0.36

geset

-0.36

POSITIVE LOGITS

ConstraintMaker

1.08

awtextra

1.00

RenderAtEndOf

0.99

 HasFactory

0.98

 BoxFit

0.92

elemField

0.89

Hentet

0.85

MLLoader

0.84

 requestCode

0.83

 viewDidLoad

0.83

Activations Density 0.122%

numerical and data-related content

No Comments

No Known Activations