INDEX

Explanations

mathematical notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

'];?>

-0.43

Nicht

-0.43

没

-0.43

』（

-0.42

nesses

-0.42

ünster

-0.42

кза

-0.41

 Chuck

-0.41

 Wikispecies

-0.41

 Schae

-0.41

POSITIVE LOGITS

 خارجية

0.79

rrggbb

0.75

Skocz

0.74

EndContext

0.69

ViewFeatures

0.68

Портал

0.66

utilisons

0.65

 StatelessWidget

0.65

principalTable

0.63

Cordialement

0.63

Activations Density 0.342%

mathematical notation and symbols

No Comments

No Known Activations