INDEX

Explanations

structural properties or classifications of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.66

you

-0.63

-0.60

-0.57

-0.54

-0.51

-0.50

div

-0.49

to

-0.49

is

-0.49

POSITIVE LOGITS

تقاوى

1.45

 Roskov

1.43

Personensuche

1.34

GEBURTSDATUM

1.31

Geplaatst

1.30

abestanden

1.30

LookAnd

1.22

rungsseite

1.20

 Мексичка

1.15

 Signalez

1.13

Activations Density 0.065%

structural properties or classifications of items

No Comments

No Known Activations