INDEX

Explanations

terms and phrases that indicate scientific findings or implications

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alphabetically

-0.54

asos

-0.51

 voeten

-0.49

 delegations

-0.49

 negation

-0.47

 symbols

-0.47

 gyrus

-0.46

 myſelf

-0.46

 sherds

-0.46

 destroyer

-0.45

POSITIVE LOGITS

awtextra

0.92

 للاسماء

0.77

Diwedd

0.69

 ProtoMessage

0.69

IsContent

0.65

おそらく

0.65

Tikang

0.64

 ***!

0.63

internalType

0.63

 ComVisible

0.61

Activations Density 0.590%

terms and phrases that indicate scientific findings or implications

No Comments

No Known Activations