INDEX

Explanations

references to New York and its associated media outlets

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

udf

-0.73

Personensuche

-0.72

sellor

-0.66

 Chengdu

-0.66

 Hoon

-0.66

paravant

-0.65

ignées

-0.63

 unlawful

-0.63

setAccessible

-0.63

 manuales

-0.63

POSITIVE LOGITS

 York

2.02

 YORK

1.68

York

1.65

 york

1.56

NY

1.52

YORK

1.40

 Yorkers

1.35

york

1.29

NY

1.23

орк

1.15

Activations Density 0.042%

references to New York and its associated media outlets

No Comments

No Known Activations