INDEX

Explanations

numbers and statistical data references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AndEndTag

-0.68

tanleria

-0.66

 صوتيه

-0.53

 protoimpl

-0.51

MemoryWarning

-0.49

nonatomic

-0.48

viewDidLoad

-0.48

crollView

-0.44

 brevity

-0.44

ExtendWith

-0.44

POSITIVE LOGITS

 Meksiku

0.71

 Roskov

0.67

 endblock

0.64

 فريبيس

0.61

WaitGroup

0.59

cristo

0.57

펴

0.55

 Herzegovina

0.55

<?>>

0.54

følgelig

0.53

Activations Density 0.601%

numbers and statistical data references

No Comments

No Known Activations