INDEX

Explanations

terms related to automation and auto-generated processes

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

 }}"></

-0.57

MessageInfo

-0.57

Jeografia

-0.56

)]:

-0.54

 Alpes

-0.52

 ivelany

-0.50

 "..\..\..\

-0.49

})();

-0.49

MergeFrom

-0.48

celine

-0.47

POSITIVE LOGITS

 Auto

0.87

 AUTO

0.85

setAuto

0.80

 Autos

0.76

 auto

0.75

Auto

0.73

Autos

0.72

 ricks

0.71

autos

0.70

autoconfigure

0.69

Activations Density 0.064%

terms related to automation and auto-generated processes

No Comments

No Known Activations