INDEX

Explanations

a variety of terms possibly relating to category labels and technical words.

oai_token-act-pair · gemini-2.0-flash

League, egg

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

egg

-0.78

 eggs

-0.71

 Eggs

-0.68

egg

-0.67

Egg

-0.66

Egg

-0.64

 league

-0.60

Eggs

-0.60

 League

-0.59

eggs

-0.56

POSITIVE LOGITS

fjspx

0.85

ंदीखरीदारी

0.80

 autorytatywna

0.78

rrggbb

0.73

 فريبيس

0.73

 AttributeSet

0.72

orteur

0.72

usermodel

0.72

 Exactos

0.71

 الرياضيه

0.70

Activations Density 8.857%

a variety of terms possibly relating to category labels and technical words.

League, egg

No Comments

No Known Activations