INDEX

Explanations

references to locations, specifically those associated with the word "North."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

XmlAccessorType

-0.88

makeConstraints

-0.70

————————————————

-0.69

Emmanuel

-0.68

 Pacer

-0.68

 Krakowie

-0.68

 Lugano

-0.68

awancara

-0.68

 Delia

-0.66

..\..\

-0.65

POSITIVE LOGITS

 North

0.90

NORTH

0.86

north

0.85

 NORTH

0.80

North

0.79

 Noth

0.79

stens

0.73

 north

0.73

 Northam

0.71

 Neub

0.67

Activations Density 0.078%

references to locations, specifically those associated with the word "North."

No Comments

No Known Activations