INDEX

Explanations

activities and historical references related to ongoing work or service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

am

-0.55

ViewImports

-0.54

nodoc

-0.53

Lähteet

-0.50

AnchorStyles

-0.50

 ferien

-0.48

ANTLR

-0.48

umptive

-0.48

 profund

-0.47

])):

-0.46

POSITIVE LOGITS

Autoritní

0.83

بوابة

0.68

ftagPool

0.67

 незавершена

0.64

XmlAccessorType

0.58

 ་་

0.56

 beginnetje

0.54

 raiſ

0.54

 anſ

0.54

 laſt

0.54

Activations Density 0.529%

activities and historical references related to ongoing work or service

No Comments

No Known Activations