INDEX

Explanations

instances of the word "York."

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

New York

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

uarts

-0.50

routeProvider

-0.48

abstractmethod

-0.48

pulseira

-0.47

 olev

-0.47

сован

-0.44

alumno

-0.44

 Dementia

-0.44

cero

-0.43

ahalli

-0.43

POSITIVE LOGITS

 York

2.00

York

1.67

 YORK

1.66

 york

1.56

york

1.31

YORK

1.29

 Yorkers

1.05

ヨーク

0.98

 Yorke

0.94

NY

0.94

Activations Density 0.009%

instances of the word "York."

New York

No Comments

No Known Activations