INDEX

Explanations

geographical names and locations, particularly related to specific regions and governmental entities

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

 clinique

-0.59

 regolare

-0.58

ObjectModel

-0.56

市镇

-0.55

 <<<<<<<<<<<<<<

-0.54

 regularity

-0.53

 inappropriés

-0.53

 plomo

-0.53

!*\

-0.51

appui

-0.51

POSITIVE LOGITS

NameInMap

0.78

 ComVisible

0.64

 bezeichneter

0.63

########.

0.62

 tartalomajánló

0.62

WebVitals

0.62

WritableDatabase

0.58

 Roskov

0.56

tagHelperRunner

0.56

 ویکی‌پدیا

0.55

Activations Density 0.852%

geographical names and locations, particularly related to specific regions and governmental entities

No Comments

No Known Activations