INDEX

Explanations

references to desired outcomes or characteristics in processes or entities

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

 newly

-0.32

])[

-0.30

 collectively

-0.30

 collective

-0.30

who

-0.29

 generally

-0.28

 common

-0.28

 famous

-0.27

 rich

-0.27

 Teil

-0.27

POSITIVE LOGITS

IUrlHelper

0.77

ModelAdmin

0.73

ViewFeatures

0.73

 Normdatei

0.70

SourceChecksum

0.70

majánló

0.70

 laſſen

0.70

 useAppContext

0.69

 zuſammen

0.69

 zwiſchen

0.69

Activations Density 0.691%

references to desired outcomes or characteristics in processes or entities

No Comments

No Known Activations