INDEX

Explanations

LaTeX markup and mathematical notation

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

}));

-0.89

Personensuche

-0.89

 disambiguazione

-0.89

RegressionTest

-0.88

 noDo

-0.82

 يتيمه

-0.78

Билгалдахарш

-0.77

 Baillargeon

-0.77

exitRule

-0.76

])).

-0.76

POSITIVE LOGITS

({\

0.77

Waz

0.71

Koo

0.68

ไ

0.66

 Heid

0.65

Zep

0.64

->__

0.64

Piz

0.64

ricane

0.64

apy

0.62

Activations Density 0.270%

LaTeX markup and mathematical notation

No Comments

No Known Activations