INDEX

Explanations

phrases indicating comparison or distinction among items

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

-0.69

 lenker

-0.66

Personendaten

-0.66

 Waray

-0.65

 Phaser

-0.64

 onAnimation

-0.63

arrive

-0.63

intios

-0.62

 ✭✭

-0.62

Datuak

-0.62

POSITIVE LOGITS

 than

0.66

 außer

0.66

 beyond

0.56

 THAN

0.55

)$}

0.54

 Than

0.53

Than

0.52

 BEYOND

0.51

 Except

0.50

 poza

0.50

Activations Density 0.295%

phrases indicating comparison or distinction among items

No Comments

No Known Activations