INDEX

Explanations

references to quantities and comparisons in terms of sufficiency or absence

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

Down

-0.51

 Betten

-0.50

__(/*!

-0.48

//

-0.48

ộ

-0.46

 onPage

-0.45

 fuori

-0.44

 plezier

-0.44

UpInside

-0.43

cluso

-0.43

POSITIVE LOGITS

 disambiguazione

0.77

ValueStyle

0.64

 يتيمه

0.64

новништво

0.62

InputBorder

0.62

 مواليد

0.59

 chi̍t

0.57

odotus

0.56

"}")

0.56

互联网档案馆

0.56

Activations Density 0.627%

references to quantities and comparisons in terms of sufficiency or absence

No Comments

No Known Activations