INDEX

Explanations

words related to alerts and notifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Audiodateien

-0.84

 Seaman

-0.71

 échanti

-0.70

 segni

-0.70

 DEPOS

-0.69

 parlent

-0.68

^\

-0.68

дован

-0.67

 uParam

-0.66

 Saxe

-0.66

POSITIVE LOGITS

 Alert

1.01

 alerts

0.97

 alert

0.94

SpringBootTest

0.89

 Alerts

0.81

wahati

0.79

cipar

0.79

alerts

0.79

SNS

0.78

 Prud

0.78

Activations Density 0.120%

words related to alerts and notifications

No Comments

No Known Activations