INDEX

Explanations

instances of the word "address."

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

numerical addresses or location identifiers in structured data.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 Mauro

-0.29

блон

-0.29

КП

-0.29

Emilia

-0.29

 Buena

-0.27

Rhestr

-0.27

getGame

-0.27

 dépens

-0.26

beforeAll

-0.26

letin

-0.26

POSITIVE LOGITS



0.82

 getAddress

0.73

httphttps

0.71

 addr

0.71

 AssemblyCompany

0.69

 setAddress

0.69

 Address

0.69

 ADDRESS

0.64

SocketAddress

0.63

addressed

0.63

Activations Density 0.110%

instances of the word "address."

numerical addresses or location identifiers in structured data.

No Comments

No Known Activations

instances of the word "address."

numerical addresses or location identifiers in structured data.

No Comments

No Known Activations