INDEX

Explanations

terms related to adhesion and attachment processes in various contexts

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

ArgsConstructor

-0.68

 متعلقه

-0.60

 kasarigan

-0.59

 câte

-0.57

 kirj

-0.56

Personendaten

-0.54

jface

-0.54

 hoek

-0.54

জন

-0.53

uestamente

-0.53

POSITIVE LOGITS

 surfaces

1.74

 surface

1.66

 Surfaces

1.45

surface

1.38

surfaces

1.36

Surface

1.25

 Surface

1.24

 SURFACE

1.19

 superficies

1.18

urface

1.18

Activations Density 0.825%

terms related to adhesion and attachment processes in various contexts

No Comments

No Known Activations