INDEX

Explanations

instances of "De" followed by another capital letter or "de" followed by another word, likely identifying names or abbreviations

oai_token-act-pair · gemini-2.0-flash

words starting with 'De'

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

De/de

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

ensement

-0.59

WaitGroup

-0.57

EndInit

-0.54

richTextPanel

-0.52

contentLoaded

-0.51

rat

-0.51

SuspendLayout

-0.50

RRect

-0.49

 multin

-0.48

 Mostly

-0.47

POSITIVE LOGITS

 ComVisible

0.59

Архівовано

0.56

клопе

0.53

posedge

0.51

 SwitchCompat

0.49

}{*}{}

0.48

ConstraintMaker

0.47

 MyBatis

0.46

lexikon

0.46

//{

0.45

Activations Density 0.128%

instances of "De" followed by another capital letter or "de" followed by another word, likely identifying names or abbreviations

words starting with 'De'

De/de

No Comments

No Known Activations