INDEX

Explanations

specific geographic locations and their associated details

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

after locations (cities/states/countries)

np_acts-logits-general · gemini-2.0-flash

location names and years

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

(-

-0.62

 Harare

-0.53

(-

-0.53

 Jiangsu

-0.51

 Danville

-0.51

$(-

-0.51

 baterai

-0.50

 (−

-0.49

==-

-0.48

 Gatwick

-0.48

POSITIVE LOGITS

 Tulsa

0.73

 ujednoznacz

0.68

 ویکی‌پدیا

0.61

IsMutable

0.60

 AttributeSet

0.60

 Kuwa

0.59

erialized

0.59

 Piel

0.58

 Kuwait

0.58

mib

0.57

Activations Density 0.083%

specific geographic locations and their associated details

after locations (cities/states/countries)

location names and years

No Comments

No Known Activations