INDEX

Explanations

numerical values and codes

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

__*/

-0.50

GEBURTS

-0.47

 sumpay

-0.44

 كومونز

-0.44

TagMode

-0.42

Coordonnées

-0.41

支

-0.41

Coh

-0.41

displayquote

-0.41

(*.

-0.40

POSITIVE LOGITS

 EconPapers

0.49

 virtudes

0.44

 convivencia

0.43

 sanitarias

0.43

 suivantes

0.42

 exhibición

0.42

 internationaux

0.41

 embarazada

0.41

 financières

0.41

chartInstance

0.41

Activations Density 0.150%

numerical values and codes

No Comments

No Known Activations