INDEX

Explanations

terms related to programming libraries and software development in a technical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

?>>

-0.62

})()

-0.53

'&:

-0.51

 ucapnya

-0.50

abilities

-0.50

︎

-0.49

 lenker

-0.48

 pronounced

-0.47

BindingSource

-0.47

 rooftops

-0.47

POSITIVE LOGITS

 BoxFit

0.83

TargetException

0.72

BeginInit

0.70

forRoot

0.64

 Италијани

0.62

Autoritní

0.62

の場合

0.60

setVerticalGroup

0.60

の場合は

0.58

 AppCompatTheme

0.57

Activations Density 0.788%

terms related to programming libraries and software development in a technical context

No Comments

No Known Activations