INDEX

Explanations

terms related to design consistency and adherence to guidelines in user interface

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

visual branding consistency

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Diwedd

-0.36

ftagPool

-0.36

FieldNumber

-0.32

verifyException

-0.32

abstractmethod

-0.31

TagMode

-0.30

########.

-0.30

тистика

-0.29

 disillusion

-0.28

aol

-0.28

POSITIVE LOGITS

 guidelines

1.20

guidelines

1.06

Guidelines

1.06

 Guidelines

1.05

 style

1.02

 Style

0.96

 guideline

0.96

 GUIDELINES

0.91

style

0.90

Style

0.87

Activations Density 0.073%

terms related to design consistency and adherence to guidelines in user interface

visual branding consistency

No Comments

No Known Activations