INDEX

Explanations

references to programming frameworks and component annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Préparation

-0.56

mopolitan

-0.56

 autorytatywna

-0.55

Affirmed

-0.55

jewództ

-0.54

ServiceTest

-0.53

исленность

-0.50

Slf

-0.50

createTextNode

-0.49

 Initialized

-0.49

POSITIVE LOGITS

@[+][

1.23

gdx

1.14

eclipse

1.08

arXiv

1.03

elemField

0.90

getValue

0.72

 }^{[

0.71

 QtWidgets

0.71

EndInit

0.71

 IndexPath

0.70

Activations Density 0.029%

references to programming frameworks and component annotations

No Comments

No Known Activations