INDEX

Explanations

specific descriptors and attributes related to products and designs

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

Text or design on clothing/objects

np_acts-logits-general · gemini-2.0-flash

designs and inscriptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

NameInMap

-0.79

ſelf

-0.78

 ſte

-0.78

exitRule

-0.75

DockStyle

-0.75

abestanden

-0.74

@"/

-0.73

 LUMP

-0.73

 uſe

-0.72

ItemBackground

-0.71

POSITIVE LOGITS

 designs

0.51

 design

0.51

 plate

0.50

بط

0.47

personalized

0.45

 plates

0.44

on

0.44

 personalized

0.44

 personalize

0.44

 patterns

0.44

Activations Density 0.207%

specific descriptors and attributes related to products and designs

Text or design on clothing/objects

designs and inscriptions

No Comments

No Known Activations