INDEX

Explanations

the prefix "Mor"

oai_token-act-pair · gemini-2.0-flash

Mor

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

atosis

-0.54

kháu

-0.46

 TestBed

-0.45

ListModule

-0.43

ttes

-0.43

AttributeSet

-0.41

ดับ

-0.41

SharedDtor

-0.41

Me

-0.40

请联系

-0.40

POSITIVE LOGITS

^(@)

0.66

存于互联网档案馆

0.60

Datuak

0.58

 kaynağından

0.56

はじめに

0.56

 FBref

0.55

IntoConstraints

0.55

consulté

0.55

!("{}",

0.54

 AssemblyProduct

0.53

Activations Density 0.191%

the prefix "Mor"

Mor

No Comments

No Known Activations