INDEX

Explanations

elements related to scientific representations, particularly in density and collaboration networks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 continúas

-0.49

enf

-0.44

 rock

-0.42

parseFrom

-0.42

xt

-0.40

バラ

-0.40

 scorso

-0.38

mml

-0.38

AutoField

-0.37

ruck

-0.37

POSITIVE LOGITS

RenderAtEndOf

0.75

</tfoot>

0.68

 فريبيس

0.68

 متعلقه

0.66

OGND

0.65

 FontWeight

0.65

Kariera

0.65

ambique

0.64

 estimés

0.64

 intStringLen

0.64

Activations Density 1.173%

elements related to scientific representations, particularly in density and collaboration networks

No Comments

No Known Activations