INDEX

Explanations

references to subsections or sections in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Balt

-0.71

avana

-0.49

ContentAlignment

-0.48

 grego

-0.48

ice

-0.47

[toxicity=0]

-0.47

 Guill

-0.47

end

-0.46

 logo

-0.45

 Esch

-0.45

POSITIVE LOGITS

subsection

4.70

subsubsection

3.50

 subsection

1.28

 subsections

1.19

ViewFeatures

1.13

 CURIAM

1.01

BibitemShut

1.00

 autorytatywna

0.97

httphttps

0.96

 Subsection

0.96

Activations Density 0.060%

references to subsections or sections in a document

No Comments

No Known Activations