INDEX

Explanations

phrases indicating frequency or quantity of occurrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

TintMode

-0.68

Lähteet

-0.64

IVEREF

-0.62

beelding

-0.57

 ouvriers

-0.56

ніципа

-0.55

DockStyle

-0.54

 hoofd

-0.54

includegraphics

-0.53

Rè

-0.53

POSITIVE LOGITS

 weeks

0.69

 days

0.68

 months

0.65

 Weeks

0.65

 Months

0.63

 wens

0.63

 season

0.62

 moun

0.62

 WEEKS

0.60

 MONTHS

0.60

Activations Density 0.185%

phrases indicating frequency or quantity of occurrence

No Comments

No Known Activations