INDEX

Explanations

specific formatted phrases or keywords, particularly in programming or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AutoresizingMask

-0.56

］

-0.54

})));

-0.53

cgi

-0.52

feira

-0.50

}}$\\

-0.49

 kant

-0.48

]},

-0.48

ارد

-0.48

opcao

-0.47

POSITIVE LOGITS

Geplaatst

0.90

vv

0.84

Дереккөздер

0.79

 Dede

0.78

popo

0.78

 popo

0.77

Tembelea

0.76

 Dodo

0.75

Nen

0.74

||=

0.74

Activations Density 1.486%

specific formatted phrases or keywords, particularly in programming or scientific contexts

No Comments

No Known Activations