INDEX

Explanations

structures or patterns typically used in mathematical expressions, particularly those involving matrices or arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 /\.(

-0.58

nsan

-0.52

endix

-0.52

Obrázky

-0.50

Portail

-0.50

eroon

-0.50

 AttributeSet

-0.49

Datuak

-0.48

FIG

-0.48

Courtney

-0.47

POSITIVE LOGITS

=>

0.76

MetaObject

0.75

 дописавши

0.72

ContentAsync

0.68

parsedMessage

0.68

ArrowToggle

0.64

DockStyle

0.63

 nhàng

0.60

AndEndTag

0.60

rungsseite

0.60

Activations Density 0.596%

structures or patterns typically used in mathematical expressions, particularly those involving matrices or arrays

No Comments

No Known Activations