INDEX

Explanations

descriptors related to aesthetics and quality of products

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

preceding specific user names

np_acts-logits-general · gemini-2.0-flash

styles and materials

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

makeText

-0.41

 okuyayım

-0.39

 становника

-0.38

argout

-0.37

UserScript

-0.36

 Colossus

-0.35

maxsize

-0.35

 Musique

-0.34

Honda

-0.32

POSITIVE LOGITS

 Reſ

0.50

ViewImports

0.49

extAlignment

0.47

 Inſ

0.47

 TextAppearance

0.47

XtraReports

0.47

 neutr

0.46

 timeless

0.46

ſelves

0.46

ſelf

0.45

Activations Density 0.175%

descriptors related to aesthetics and quality of products

preceding specific user names

styles and materials

No Comments

No Known Activations