INDEX

Explanations

references to personal favorites or preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 getInstance

-0.44

คม

-0.44

LookAnd

-0.44

NOS

-0.42

átu

-0.41

IVersion

-0.40

noo

-0.39

 Biôgrafia

-0.39

 saman

-0.39

getInstance

-0.39

POSITIVE LOGITS

 favorite

3.06

 favourite

2.78

 favorites

2.62

favorite

2.57

 Favorite

2.46

 FAVORITE

2.38

 favourites

2.35

favourite

2.31

Favorite

2.24

 Favourite

2.23

Activations Density 0.134%

references to personal favorites or preferences

No Comments

No Known Activations