INDEX

Explanations

the word "by" as well as words near the word "by"

oai_token-act-pair · gemini-2.0-flash

by

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 pinulongan

-0.76

 مشين

-0.66

 onCreateView

-0.63

 AssemblyCompany

-0.60

 unknownFields

-0.58

reportWebVitals

-0.58

 StatefulWidget

-0.57

 متعلقه

-0.57

 يتيمه

-0.56

 FontWeight

-0.56

POSITIVE LOGITS

<bos>

1.07

endphp

0.55

MockBean

0.54

OGND

0.54

 Савезне

0.50

achal

0.48

ographia

0.47

queryInterface

0.47

lamabad

0.47

applique

0.47

Activations Density 8.915%

the word "by" as well as words near the word "by"

by

No Comments

No Known Activations