INDEX

Explanations

references to length measurements or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

BeginContext

-0.75

ngdoc

-0.64

jface

-0.59

GEBURTSDATUM

-0.58

 itinéraires

-0.56

bootstrapcdn

-0.55

IContainer

-0.54

MessageTagHelper

-0.53

PhysRev

-0.51

gráfico

-0.50

POSITIVE LOGITS

 length

2.40

 Length

2.02

 lengths

1.89

 LENGTH

1.74

 lenght

1.54

Length

1.54

 Länge

1.45

Lengths

1.32

ength

1.28

 longueur

1.26

Activations Density 0.133%

references to length measurements or specifications

No Comments

No Known Activations