INDEX

Explanations

references to layout configurations in a graphical or programming context

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

layout

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 ویکی‌پدی

-0.61

 henkil

-0.56

ennemi

-0.55

 médicale

-0.55

 étranger

-0.53

astéro

-0.51

 extranjera

-0.49

 cinquième

-0.49

withCredentials

-0.48

 tenisky

-0.48

POSITIVE LOGITS

 Layout

1.48

 layout

1.41

 LAYOUT

1.39

Layout

1.39

layout

1.35

LAYOUT

1.26

 layouts

1.22

ayout

1.12

getLayout

1.07

 getLayout

1.04

Activations Density 0.007%

references to layout configurations in a graphical or programming context

layout

No Comments

No Known Activations