INDEX

Explanations

terms related to licensing, copyright, and configuration in software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 שוליים

-0.39

bootstrapcdn

-0.39

]='\

-0.36

SpringBootTest

-0.34

displayquote

-0.33

])):

-0.32

Inv

-0.31

 الحره

-0.31

 prop

-0.30

occup

-0.30

POSITIVE LOGITS

$_['

1.34

adaptiveStyles

0.69

tinyos

0.64

 ModelRenderer

0.60

 uLocal

0.57

AndEndTag

0.57

NameInMap

0.55

ActionCreators

0.54

PropertyChanging

0.52

Vidite

0.52

Activations Density 0.005%

terms related to licensing, copyright, and configuration in software

No Comments

No Known Activations