INDEX

Explanations

capitalized abbreviations, or names beginning with the letter "M" or "N"

oai_token-act-pair · gemini-2.0-flash

the presence of the token 'Man'

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

Swaziland/Eswatini context

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

 nakalista

-0.58

 otomatig

-0.54

nvarchar

-0.53

frica

-0.51

aires

-0.47

 vậy

-0.47

Примітки

-0.46

Erreferentziak

-0.45

 Winaray

-0.45

 AssemblyCulture

-0.45

POSITIVE LOGITS

 sahiptir

0.58

 magnétique

0.55

 lipoprotein

0.55

 disambiguazione

0.54

 politics

0.54

 unknownFields

0.51

 poros

0.50

 StatelessWidget

0.49

ädie

0.49

 chromos

0.49

Activations Density 0.136%

capitalized abbreviations, or names beginning with the letter "M" or "N"

the presence of the token 'Man'

Swaziland/Eswatini context

No Comments

No Known Activations