INDEX

Explanations

layout-related terms in user interface design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

SourceChecksum

-0.93

AndroidJUnit

-0.82

TagMode

-0.81

fjspx

-0.79

Enllaces

-0.75

 propOrder

-0.75

ValueGeneration

-0.74

expandindo

-0.73

Хьажоргаш

-0.72

 protoimpl

-0.69

POSITIVE LOGITS

 BorderLayout

2.20

BorderLayout

1.84

SupportActionBar

0.84

 WaitForSeconds

0.66

 digress

0.66

zyp

0.55

ற்க

0.51

govia

0.51

 gouvern

0.50

barco

0.50

Activations Density 0.002%

layout-related terms in user interface design

No Comments

No Known Activations