INDEX

Explanations

references to organizational roles and responsibilities in professional settings

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

after titles or positions

np_acts-logits-general · gemini-2.0-flash

administrative roles and functions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

########.

-0.65

CloseOperation

-0.60

 Référence

-0.56

bootstrapcdn

-0.52

 بيها

-0.52

tahui

-0.52

endimento

-0.51

jš

-0.50

 vetorial

-0.50

 gratuitas

-0.49

POSITIVE LOGITS

 administrative

1.65

 marketing

1.47

 Administrative

1.40

administrative

1.33

 Marketing

1.30

 administration

1.29

Administrative

1.25

 admin

1.24

Marketing

1.24

 administrativa

1.23

Activations Density 0.303%

references to organizational roles and responsibilities in professional settings

after titles or positions

administrative roles and functions

No Comments

No Known Activations