INDEX

Explanations

IP-related terms and protocols

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

-0.84

IsInitialized

-0.84

 autorytatywna

-0.83

MigrationBuilder

-0.83

 Italijanski

-0.79

 mergeFrom

-0.78

 الرياضيه

-0.78

oredCriteria

-0.74

 consuls

-0.74

parsedMessage

-0.73

POSITIVE LOGITS

IP

0.79

ip

0.70

IP

0.66

IPs

0.62

Ip

0.61

 address

0.59

ip

0.58

address

0.58

 addresses

0.56

Ips

0.56

Activations Density 0.136%

IP-related terms and protocols

No Comments

No Known Activations