INDEX

Explanations

words or names starting with "Gri", "Nutri", "Patri", "Matri", "Di", or "Depre"

oai_token-act-pair · gemini-2.0-flash

various specific mentions

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

 mouseY

-0.67

trice

-0.56

EndTag

-0.55

Datuak

-0.54

atrième

-0.52

findpost

-0.52

 سكانية

-0.52

 minds

-0.52

lös

-0.51

tagext

-0.51

POSITIVE LOGITS

 estimés

0.70

 للاسماء

0.50

WindowListener

0.46

 nærm

0.45

OOTDTY

0.44

 manqué

0.44

 jsPsych

0.42

ầng

0.42

Linki

0.42

 znaczy

0.42

Activations Density 0.693%

words or names starting with "Gri", "Nutri", "Patri", "Matri", "Di", or "Depre"

various specific mentions

No Comments

No Known Activations