INDEX

Explanations

references to specific authors, works, and artistic styles

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Art, literature, and music (artists and genres)

np_acts-logits-general · gemini-2.0-flash

surreal art and literature

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

Negative Logits

Personensuche

-0.55

Tikang

-0.54

✨:

-0.54

ɵɵ

-0.50

celotti

-0.49

WriteTagHelper

-0.49

:✨

-0.49

sweat

-0.49

談社

-0.49

kuuta

-0.48

POSITIVE LOGITS

 defaultstate

0.49

AlterField

0.44

ampunk

0.44

 Gothic

0.40

 surreal

0.39

 gothic

0.38

 usług

0.36

 eccentric

0.36

 steampunk

0.35

scalatest

0.34

Activations Density 0.532%

references to specific authors, works, and artistic styles

Art, literature, and music (artists and genres)

surreal art and literature

No Known Activations