INDEX

Explanations

phrases indicating quantities or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ske

-0.54

 Basta

-0.54

 thereunder

-0.54

 assic

-0.53

шер

-0.52

 duly

-0.51

 Milan

-0.50

latego

-0.49

 accordingly

-0.49

})_{

-0.48

POSITIVE LOGITS

 amount

0.88

 ligiloj

0.83

tagHelperRunner

0.81

rungsseite

0.69

 disambiguazione

0.69

amount

0.69

EDEFAULT

0.68

OGND

0.68

Controllo

0.68

ViewImports

0.66

Activations Density 0.269%

phrases indicating quantities or counts

No Comments

No Known Activations