INDEX

Explanations

references to locations and geographic entities in Florida

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

öszi

-0.69

DeleteBehavior

-0.68

 Mongolian

-0.67

ⓧ

-0.67

 Jurí

-0.67

 Uribe

-0.66

wickshire

-0.65

kyou

-0.64

 Económica

-0.64

yntaxException

-0.63

POSITIVE LOGITS

 Florida

1.26

Florida

1.19

 Orlando

1.13

Orlando

1.10

 FLORIDA

1.01

 florida

0.95

 orlando

0.88

 Tampa

0.88

florida

0.82

FLOR

0.81

Activations Density 0.434%

references to locations and geographic entities in Florida

No Comments

No Known Activations