INDEX

Explanations

references to classified ads and listings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

advertising or job postings

np_acts-logits-general · gemini-2.0-flash

classified ads and listings

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RetentionPolicy

-0.65

omock

-0.63

 AppCompatTheme

-0.61

 '\\;'

-0.61

يكب

-0.61

OrBuilder

-0.60

الدراسه

-0.60

EDEFAULT

-0.59

IUrlHelper

-0.58

Дереккөздер

-0.56

POSITIVE LOGITS

ads

1.43

 advertisements

1.39

 advertisement

1.39

 advertise

1.38

 listings

1.34

 listing

1.31

 adverts

1.28

 advertising

1.28

 advertised

1.27

 advert

1.26

Activations Density 0.162%

references to classified ads and listings

advertising or job postings

classified ads and listings

No Comments

No Known Activations