INDEX

Explanations

instances of direct address or engagement with the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

だったが

-0.80

发表于

-0.75

 ویکی‌پدی

-0.71

SourceChecksum

-0.67

 AssemblyTitle

-0.67

だが

-0.66

setopt

-0.66

 فريبيس

-0.64

存于互联网档案馆

-0.64

 ihren

-0.63

POSITIVE LOGITS

 yourself

2.02

 yourselves

1.50

yourself

1.48

 your

1.43

 Yourself

1.41

 YOURSELF

1.34

your

1.24

Yourself

1.16

Your

1.06

 Your

1.02

Activations Density 0.695%

instances of direct address or engagement with the reader

No Comments

No Known Activations