INDEX

Explanations

words related to conducting or writing about research

oai_token-act-pair · gemini-2.0-flash

research significance

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

BASEPATH

-0.50

 AttributeSet

-0.49

uropa

-0.48

例句

-0.48

WithIdentifier

-0.47

 <>",

-0.47

regeln

-0.47

 ModelExpression

-0.46

MessageOf

-0.46

homonymie

-0.45

POSITIVE LOGITS

 AssemblyCompany

0.70

AddField

0.54

Manbalar

0.53

 thereof

0.52

ImageContext

0.52

InputTagHelper

0.51

 betweenstory

0.50

 Paglinawan

0.50

fällig

0.49

 whereof

0.48

Activations Density 2.563%

words related to conducting or writing about research

research significance

No Comments

No Known Activations