INDEX

Explanations

varied, but generally proper nouns and other terminology related to people's lives, particularly when multiple occur in a short span.

oai_token-act-pair · gemini-2.0-flash

Living/Residence

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

 living

-3.03

living

-2.77

 Living

-2.73

Living

-2.73

 live

-2.67

live

-2.45

 LIVING

-2.45

Live

-2.39

 lived

-2.38

 Live

-2.38

POSITIVE LOGITS

 DBNull

0.57

 مرئيه

0.57

leau

0.46

存于互联网档案馆

0.46

ði

0.45

enga

0.45

ANGA

0.44

cyklopedia

0.44

 OMITTED

0.44

SPARENT

0.43

Activations Density 3.207%

varied, but generally proper nouns and other terminology related to people's lives, particularly when multiple occur in a short span.

Living/Residence

No Comments

No Known Activations