INDEX

Explanations

words related to electronic displays and file formats

oai_token-act-pair · gemini-2.0-flash

specific terms likely related to technical or coding formats

np_token-act-pair-logits · gpt-4o-mini

Code/Markup

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ufficio

-0.57

LookAnd

-0.56

 soprav

-0.51

évaluateur

-0.50

ReusableCell

-0.49

RenderAtEndOf

-0.49

 preved

-0.49

].)

-0.49

PointerException

-0.47

χεία

-0.47

POSITIVE LOGITS

GEBURTSDATUM

0.76

 betweenstory

0.59

 esternos

0.59

InjectMocks

0.59

embre

0.59

Lähteet

0.55

WriteTagHelper

0.55

 CURLOPT

0.55

 pinulongan

0.54

Enllaces

0.53

Activations Density 2.488%

words related to electronic displays and file formats

specific terms likely related to technical or coding formats

Code/Markup

No Comments

No Known Activations