INDEX

Explanations

references to vehicles and automotive features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

CrossRef

-0.61

atuor

-0.55

endpush

-0.54

OGND

-0.53

ioutil

-0.52

+:+

-0.50

ništ

-0.49

providedIn

-0.47

 lenker

-0.47

forChild

-0.46

POSITIVE LOGITS

IBOutlet

0.85

Hochspringen

0.83

AnchorTagHelper

0.65

 mẽ

0.60

 totem

0.60

aarrggbb

0.58

ecé

0.56

 تضيفلها

0.56

orianCalendar

0.55

enerys

0.54

Activations Density 1.257%

references to vehicles and automotive features

No Comments

No Known Activations