INDEX

Explanations

code syntax having to do with react, including setState, component, and render

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

uur

-0.44

ORT

-0.43

Mas

-0.42

instancetype

-0.42

 ارش

-0.42

OB

-0.41

 NSCoder

-0.41

 McCarthy

-0.40

umbi

-0.40

Line

-0.40

POSITIVE LOGITS

 ModelExpression

0.77

PMailer

0.76

XmlAccessType

0.73

Diwedd

0.72

__":

0.70

prefixer

0.67

rungsseite

0.66

NgModule

0.66

WithIOException

0.65

__':

0.65

Activations Density 0.370%

code syntax having to do with react, including setState, component, and render

code

No Comments

No Known Activations