INDEX

Explanations

words and phrases pertaining to data collection and study analysis

oai_token-act-pair · gemini-2.0-flash

data

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Signalez

-0.61

']):

-0.57

colhead

-0.52

zubauen

-0.51

hdashline

-0.49

描

-0.49

'])

-0.46

"];

-0.46

ConstraintMaker

-0.46

)]:

-0.45

POSITIVE LOGITS

Carriera

0.73

 surla

0.63

RegistryLite

0.58

EndGlobalSection

0.56

Сылтамалар

0.56

complexContent

0.54

 vectorielle

0.54

 Roskov

0.53

ьаж

0.52

 nonatomic

0.52

Activations Density 2.450%

words and phrases pertaining to data collection and study analysis

data

No Comments

No Known Activations