INDEX

Explanations

mentions of New York City, especially Brooklyn and Manhattan, as well as contextual words like "in" "to" and words denoting artistic activity.

oai_token-act-pair · gemini-2.0-flash

New York City

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.98

Personensuche

-0.88

ftagPool

-0.83

MetaObject

-0.79

MessageTagHelper

-0.73

MemoryWarning

-0.71

///</

-0.70

 typelib

-0.68

 صوتيه

-0.67

ParallelGroup

-0.66

POSITIVE LOGITS

Nol

0.55

Gow

0.52

Tri

0.50

Tri

0.49

yectos

0.48

 Lower

0.48

Duane

0.46

Dum

0.45

cotta

0.45

Lower

0.44

Activations Density 1.000%

mentions of New York City, especially Brooklyn and Manhattan, as well as contextual words like "in" "to" and words denoting artistic activity.

New York City

No Comments

No Known Activations