INDEX

Explanations

words and phrases related to acquiring products, brands, discounts, and shopping opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Personendaten

-0.62

]&

-0.61

ospel

-0.57

}&

-0.57

SequentialGroup

-0.56

]**

-0.55

XmlRootElement

-0.55

 OnClickListener

-0.54

klä

-0.54



-0.53

POSITIVE LOGITS

StoreMessageInfo

0.63

ագրություններ

0.55

,,

0.54

Inches

0.54

fó

0.53

pite

0.52

 pulumi

0.51

<%=

0.51

ո

0.50

 along

0.50

Activations Density 0.127%

words and phrases related to acquiring products, brands, discounts, and shopping opportunities

No Comments

No Known Activations