INDEX

Explanations

references to grid structures in various contexts

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

"grid" (often capitalized)

np_acts-logits-general · gemini-2.0-flash

grid and related spatial structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endphp

-1.23

 مشين

-0.99

PhysRevD

-0.97

 AssemblyProduct

-0.94

Personensuche

-0.91

tvguidetime

-0.90

 تضيفلها

-0.89

NOK

-0.86

makeText

-0.86

DrawerToggle

-0.84

POSITIVE LOGITS

 grid

1.45

 Grid

1.39

 grids

1.33

Grid

1.29

grid

1.27

 GRID

1.11

GRID

1.10

grids

0.96

isGrid

0.84

グリ

0.83

Activations Density 0.133%

references to grid structures in various contexts

"grid" (often capitalized)

grid and related spatial structures

No Comments

No Known Activations