INDEX

Explanations

descriptors related to aesthetics and appearances in objects and designs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AspNetCore

-0.81

 AssemblyCompany

-0.80

 ModelExpression

-0.76

RenderAtEndOf

-0.74

 متعلقه

-0.73

Datuak

-0.72

rawDesc

-0.71

CppMethod

-0.71

mybatisplus

-0.70

routeProvider

-0.69

POSITIVE LOGITS

 look

1.81

look

1.47

 appearance

1.45

 looks

1.37

 Look

1.28

Look

1.21

 feel

1.20

 LOOK

1.18

 style

1.15

 vibe

1.11

Activations Density 0.241%

descriptors related to aesthetics and appearances in objects and designs

No Comments

No Known Activations