INDEX

Explanations

words and phrases related to advertising and web addresses

oai_token-act-pair · gemini-2.0-flash

website-related content

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

 anomalous

-0.46

 decaying

-0.45

 rodents

-0.42

########.

-0.42

 pettico

-0.42

 mounds

-0.42

 lichen

-0.41

 degeneration

-0.41

 decayed

-0.41

 runoff

-0.40

POSITIVE LOGITS

bootstrapcdn

0.80

+:+

0.69

出版年

0.63

gameserver

0.63

 GenerationType

0.63

ControllerAdvice

0.62

TargetException

0.61

 Urdu

0.58

djangoproject

0.57

esModule

0.57

Activations Density 41.787%

words and phrases related to advertising and web addresses

website-related content

No Comments

No Known Activations