INDEX

Explanations

percentages and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

guiente

-0.48

 Svensson

-0.46

ViewImports

-0.46

LESSON

-0.44

 gonzález

-0.44

tonsoft

-0.41

única

-0.41

 extras

-0.39

conclusion

-0.39

oneofs

-0.39

POSITIVE LOGITS

 contain

0.52

 possess

0.50

aarrggbb

0.48

bcryptjs

0.48

Autoritní

0.47

FontOfSize

0.46

addContainerGap

0.45

TabStop

0.45

 possesses

0.45

Marine

0.44

Activations Density 0.073%

percentages and statistical data

No Comments

No Known Activations