INDEX

Explanations

parts of emails or names and handles

oai_token-act-pair · gemini-2.0-flash

forum posts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

transQ

-0.71

 StatefulWidget

-0.68

 Mawr

-0.65

 Gaga

-0.60

ьаж

-0.60

Parcelize

-0.59

Vidite

-0.57

 Twain

-0.57

 EXISTS

-0.56

verwijspagina

-0.56

POSITIVE LOGITS

 giusti

0.47

powers

0.47

 figliu

0.45

Branch

0.44

addCriterion

0.42

 booth

0.42

collier

0.41

banks

0.40

 hoek

0.40

Thomas

0.40

Activations Density 3.642%

parts of emails or names and handles

forum posts

No Comments

No Known Activations