INDEX

Explanations

phrases and concepts related to measurements and factors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 noqa

-0.75

+#+#

-0.73

帖最后由

-0.72

 <<<<<<<<<<<<<<

-0.69

 "..\..\

-0.68

 IBOutlet

-0.65

AutoScale

-0.65

matchCondition

-0.65

LayoutStyle

-0.63

ineno

-0.62

POSITIVE LOGITS

of

0.71

 ―――――

0.63

 itſelf

0.56

φάλ

0.55

 Houſe

0.52

 της

0.51

 moschino

0.51

 myſelf

0.49

 ſever

0.49

Eſ

0.48

Activations Density 2.306%

phrases and concepts related to measurements and factors in various contexts

No Comments

No Known Activations