INDEX

Explanations

references to educational or professional affiliations and roles

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

 pioneered

-0.42

 houve

-0.41

mpty

-0.39

(_.

-0.38

 dependencia

-0.37

 sní

-0.36

 monitores

-0.36

 daun

-0.36

endió

-0.36

вича

-0.36

POSITIVE LOGITS

 незавершена

1.00

 <=",

0.97

SharedDtor

0.92

ьаж

0.83

 AssemblyTitle

0.81

VersionUID

0.81

цездатний

0.80

 >=",

0.78

IUrlHelper

0.78

titleMargin

0.76

Activations Density 0.252%

references to educational or professional affiliations and roles

No Comments

No Known Activations