INDEX

Explanations

elements related to image and logo presentation within HTML content

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

Code and markup syntax

np_acts-logits-general · gemini-2.0-flash

UI sizing and code attributes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

writerow

-0.58

enumi

-0.56

Autoritní

-0.50

 vân

-0.48

transQ

-0.48

 AssemblyCulture

-0.48

abcdefghijklmnop

-0.46

ülen

-0.45

nEnter

-0.45

AxisAlignment

-0.44

POSITIVE LOGITS

ArgsConstructor

0.73

 BoxFit

0.62

 Sizing

0.59

下载附件

0.57

 AssemblyProduct

0.56

 sizing

0.56

 שוליים

0.55

Wart

0.55

 Portraits

0.54

 erad

0.54

Activations Density 0.082%

elements related to image and logo presentation within HTML content

Code and markup syntax

UI sizing and code attributes

No Comments

No Known Activations