INDEX

Explanations

references to "series" in various contexts, possibly indicating sequencing or serialized content

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

脚注の使い方

-0.74

 notizia

-0.65

lihood

-0.62

avax

-0.62

cshtml

-0.60

Ouch

-0.60

heast

-0.59

 toothpick

-0.59

存于互联网档案馆

-0.58

ysacchar

-0.58

POSITIVE LOGITS

 series

3.68

 Series

3.38

Series

3.32

 SERIES

3.23

series

3.23

SERIES

2.85

 serie

2.42

 série

2.23

Serie

2.13

 séries

2.12

Activations Density 0.035%

references to "series" in various contexts, possibly indicating sequencing or serialized content

No Comments

No Known Activations