INDEX

Explanations

code-related terms associated with layout and alignment in web design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Ker

-0.49

ene

-0.46

 BorderRadius

-0.45

Ser

-0.44

 anyag

-0.43

lek

-0.43

id

-0.43

サイン

-0.42

ser

-0.42

van

-0.42

POSITIVE LOGITS

ISupport

1.23

SequentialGroup

1.13

 pleaſure

1.06

RegressionTest

1.06

openqa

1.01

Kanpo

0.99

DoubleQuotes

0.97

^(@)

0.97

 itſelf

0.96

новништво

0.96

Activations Density 0.014%

code-related terms associated with layout and alignment in web design

No Comments

No Known Activations