INDEX

Explanations

references to records and recording activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SequentialGroup

-0.81

 BeautifulSoup

-0.77

 Gilli

-0.75

DispatchToProps

-0.75

PREFACE

-0.74

pherals

-0.72

Же

-0.71

PyExc

-0.70

 rami

-0.70

Tembelea

-0.70

POSITIVE LOGITS

 record

2.79

 Record

2.79

record

2.65

Record

2.64

 records

2.58

 RECORD

2.58

records

2.38

 Records

2.31

RECORD

2.29

Records

2.28

Activations Density 0.088%

references to records and recording activities

No Comments

No Known Activations