INDEX

Explanations

corporate and product-related terms

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

company activities

np_acts-logits-general · gemini-2.0-flash

invention and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 الحره

-0.67

ChildScrollView

-0.52

Organizer

-0.52

 chi̍t

-0.51

Ecotoxicity

-0.50

urlpatterns

-0.49

 fırs

-0.49

 otomatig

-0.49

strtotime

-0.48

<_>

-0.48

POSITIVE LOGITS

 designing

1.31

 manufacture

1.26

 manufacturing

1.26

 design

1.18

 designers

1.18

 engineers

1.15

Designing

1.13

研发

1.11

開発

1.11

 inventing

1.09

Activations Density 0.480%

corporate and product-related terms

company activities

invention and design

No Comments

No Known Activations