INDEX

Explanations

names and roles of actors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 almacenamiento

-0.46

 adquisición

-0.46

 conformidad

-0.46

 peme

-0.45

 penyimpanan

-0.44

 nutrición

-0.42

 nettoyage

-0.41

 térmica

-0.40

 evolución

-0.40

RefNanny

-0.40

POSITIVE LOGITS

delwed

0.47

 portraits

0.47

rrggbb

0.47

Hentet

0.47

 crayfish

0.46

 portrait

0.45

fxml

0.44

⤹

0.44

ItemBackground

0.44

 Portrait

0.43

Activations Density 0.136%

names and roles of actors

No Comments

No Known Activations