INDEX

Explanations

references to geographical locations, specifically cities and associated entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Manbalar

-0.68

webElementGuid

-0.64

ANSA

-0.64

SourceChecksum

-0.63

 الرياضيه

-0.62

TemporalType

-0.60

HCL

-0.60

cionario

-0.59

Mab

-0.58

Rüyada

-0.56

POSITIVE LOGITS

 Hong

1.56

 Kong

1.39

 Hongkong

1.38

 Singapore

1.37

APORE

1.32

Hong

1.26

Singapore

1.18

 KONG

1.16

Kong

1.12

 hong

1.09

Activations Density 0.049%

references to geographical locations, specifically cities and associated entities

No Comments

No Known Activations