INDEX

Explanations

references to interior and exterior elements, particularly in the context of design or description

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+:+

-0.87

WAUKEE

-0.81

 HasFactory

-0.77

 Recife

-0.76

PAIGN

-0.76

 mesurer

-0.75

accumulative

-0.74

illoma

-0.74

//

-0.73

 flanges

-0.73

POSITIVE LOGITS

 interior

1.84

 Interior

1.77

Interior

1.71

 INTERIOR

1.69

interior

1.66

 interiors

1.62

 Interiors

1.37

nterior

1.35

INTERIOR

1.31

 Exterior

1.26

Activations Density 0.135%

references to interior and exterior elements, particularly in the context of design or description

No Comments

No Known Activations