INDEX

Explanations

references to legal terms and processes

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

"Map" or "maps" followed by another word

np_acts-logits-general · gemini-2.0-flash

map

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

msgSender

-0.55

 oprot

-0.53

fromCharCode

-0.51

WebVitals

-0.49

 IBOutlet

-0.48

getWriter

-0.48

+:+

-0.47

})`

-0.46

serviceWorker

-0.46

IntoConstraints

-0.46

POSITIVE LOGITS

map

4.05

Map

3.71

map

3.52

Map

3.50

 maps

3.14

 Maps

2.85

 mapping

2.80

MAP

2.75

MAP

2.71

 mapped

2.65

Activations Density 0.197%

references to legal terms and processes

"Map" or "maps" followed by another word

map

No Comments

No Known Activations