INDEX

Explanations

references to the concept of "one" or uniqueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

matchCondition

-0.43

Życiorys

-0.43

 lebaran

-0.39

 terpisah

-0.36

 HttpHeaders

-0.35

 なり

-0.35

suc

-0.35

Autoritní

-0.35

 Giochi

-0.34

硃

-0.34

POSITIVE LOGITS

One

0.73

One

0.70

ONE

0.69

ONE

0.68

getOne

0.67

 onep

0.66

updateOne

0.57

one

0.56

ワン

0.54

 Одно

0.52

Activations Density 0.378%

references to the concept of "one" or uniqueness

No Comments

No Known Activations