INDEX

Explanations

periods and punctuation that indicate sentence endings or breaks in thought

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 myſelf

-0.76

ValueStyle

-0.74

 itſelf

-0.74

 purpoſe

-0.71

 faſt

-0.69

 importantly

-0.69

 Houſe

-0.68

 himſelf

-0.67

 pleaſure

-0.67

HtmlAttribute

-0.66

POSITIVE LOGITS

But

0.50

but

0.46

noh

0.46

DOCTYPE

0.45

 doubtless

0.44

 scarcely

0.44

ibut

0.43

ifs

0.42

 הלא

0.42

kolen

0.40

Activations Density 0.549%

periods and punctuation that indicate sentence endings or breaks in thought

No Comments

No Known Activations