INDEX

Explanations

names and titles from a specific media franchise

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

flav

-0.46

Ằ

-0.45

__).

-0.43

heft

-0.42

 flavour

-0.41

 flavor

-0.40

</tfoot>

-0.38

 Fundraising

-0.38

INCREF

-0.38

cd

-0.38

POSITIVE LOGITS

 يتيمه

0.59

 Administrativna

0.49

 Paglinawan

0.48

معلومات

0.46

 EconPapers

0.46

 linkovi

0.44

 utafitiHapana

0.43

SpringRunner

0.40

parsedMessage

0.40

Personendaten

0.40

Activations Density 0.243%

names and titles from a specific media franchise

No Comments

No Known Activations