INDEX

Explanations

references to scientific journals and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

[](

-0.51

ereum

-0.46

󠁢

-0.46

 City

-0.44

muth

-0.44

</h4>

-0.43

antMatchers

-0.43

setDuration

-0.42

htdocs

-0.41

multer

-0.41

POSITIVE LOGITS

ьаж

0.91

HostException

0.77

gonic

0.70

 pegat

0.70

titleMargin

0.69

windowFixed

0.68

rungsseite

0.68

">—

0.67

IsInitialized

0.66

WithIOException

0.66

Activations Density 0.938%

references to scientific journals and articles

No Comments

No Known Activations