INDEX

Explanations

programming and layout terminology in relation to UI design

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

Code related to box dimensions

np_acts-logits-general · gemini-2.0-flash

width, height, dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

glLoad

-0.36

orianCalendar

-0.36

สา

-0.35

itinéraire

-0.35

 الوطنيه

-0.34

 desecha

-0.34

NOSTIC

-0.33

moveToFirst

-0.32

ionale

-0.32

 hoang

-0.32

POSITIVE LOGITS

 width

1.62

 Width

1.43

width

1.32

 height

1.30

 widths

1.28

Width

1.21

 dimensions

1.12

 Height

1.10

 WIDTH

1.09

height

1.06

Activations Density 0.272%

programming and layout terminology in relation to UI design

Code related to box dimensions

width, height, dimensions

No Comments

No Known Activations