INDEX

Explanations

entities and concepts associated with "Central" or similar terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Filipinas

-0.81

 moons

-0.76

 Dolom

-0.76

 Uttarakhand

-0.75

ècie

-0.75

 Trooper

-0.74

 Roskov

-0.74

Phillips

-0.72

 comets

-0.71

 Sikkim

-0.70

POSITIVE LOGITS

 Central

1.75

Central

1.66

 central

1.60

central

1.57

 CENTRAL

1.54

CENTRAL

1.53

 centrales

1.31

 Centra

1.26

 centrale

1.26

centr

1.21

Activations Density 0.049%

entities and concepts associated with "Central" or similar terms

No Comments

No Known Activations