INDEX

Explanations

words associated with commonness and frequency in various contexts

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

idać

-0.62

 nucléaire

-0.55

 avulla

-0.54

 vicino

-0.54

 kanssa

-0.50

 köt

-0.49

 különböz

-0.48

cemment

-0.48

Clos

-0.47

 frequenza

-0.47

POSITIVE LOGITS

rungsseite

0.94

 original

0.94

webElementXpaths

0.81

 Réponses

0.78

 المعيارى

0.78

IVEREF

0.78

 unknownFields

0.78

parsedMessage

0.78

 AssemblyCompany

0.76

}')

0.73

Activations Density 0.382%

words associated with commonness and frequency in various contexts

No Comments

No Known Activations