INDEX

Explanations

mathematical expressions and symbols used in technical documentation

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

 Authenticity

-0.60

 discogs

-0.54

 OFDb

-0.53

ropshire

-0.53

 مُعرِّف

-0.52

 Mahabhar

-0.52

openzeppelin

-0.52

 Legendre

-0.51

 }}"></

-0.51

 validamos

-0.51

POSITIVE LOGITS

 ويكيميديا

0.59

tplatz

0.54

 noqa

0.54

urlpatterns

0.52

erii

0.51

jooq

0.50

ashiro

0.50

DeleteBehavior

0.49

 mission

0.49

ỡng

0.49

Activations Density 2.706%

mathematical expressions and symbols used in technical documentation

No Comments

No Known Activations