INDEX

Explanations

phrases indicating awareness or knowledge about something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

UnsafeEnabled

-0.67

RSpec

-0.64

ViewChild

-0.63

󠁢

-0.62

xase

-0.61

ArrowToggle

-0.60

LLocation

-0.60

UpInside

-0.60

Obrázky

-0.57

ngua

-0.56

POSITIVE LOGITS

bcryptjs

0.56

ளை

0.51

veratrol

0.49

ंदीखरीदारी

0.49

baz

0.48

年には

0.48

 Vries

0.48

spreis

0.47

竟然

0.46

bbene

0.46

Activations Density 0.269%

phrases indicating awareness or knowledge about something

No Comments

No Known Activations