INDEX

Explanations

terms related to office documents and applications, primarily Microsoft Word and creating stationery.

oai_token-act-pair · gemini-2.0-flash

terms related to digital documentation or planning

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

Planning and office supplies

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

 EconPapers

-0.56

NOPQRST

-0.55

PerformLayout

-0.55

 Италијани

-0.53

:✨

-0.52

 defaultstate

-0.48

endiri

-0.48

 liitty

-0.46

EventHandler

-0.45

 batteri

-0.45

POSITIVE LOGITS

 moles

0.62

godic

0.58

Page

0.58

 planners

0.57

scriptcase

0.57

 Page

0.56

 initComponents

0.55

page

0.55

 Pages

0.54

 page

0.54

Activations Density 2.357%

terms related to office documents and applications, primarily Microsoft Word and creating stationery.

terms related to digital documentation or planning

Planning and office supplies

No Comments

No Known Activations