INDEX

Explanations

artistic expressions and techniques that highlight manipulation and dimensionality in works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Chriftian

-0.73

 purpoſe

-0.71

 houſe

-0.70

 Jefus

-0.69

 fubject

-0.67

 officielles

-0.65

rąg

-0.65

Efq

-0.63

 Reſ

-0.62

 reaſon

-0.62

POSITIVE LOGITS

 cherchés

0.57

verwijspagina

0.55

 relationships

0.54

 viewType

0.52

 shapes

0.51

 للاسماء

0.51

 consultato

0.50

LAB

0.50

 explores

0.49

 reclaimed

0.49

Activations Density 0.147%

artistic expressions and techniques that highlight manipulation and dimensionality in works

No Comments

No Known Activations