INDEX

Explanations

locations or entities related to organizations or places

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

Location names, often in the United States

np_acts-logits-general · gemini-2.0-flash

New York locations and USA

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

ázaro

-0.58

 Jacinto

-0.56

 CanadaChoose

-0.56

 Cand

-0.55

حال

-0.53

airro

-0.52

 EconPapers

-0.51

vestres

-0.51

iredo

-0.50

ítulos

-0.50

POSITIVE LOGITS

 Bronx

0.66

 Westchester

0.63

клопе

0.62

 Riverdale

0.57

 MotionEvent

0.56

Bron

0.47

 BRON

0.47

addCriterion

0.47

landt

0.46

Panamoan

0.46

Activations Density 0.167%

locations or entities related to organizations or places

Location names, often in the United States

New York locations and USA

No Comments

No Known Activations