INDEX

Explanations

alerts and warnings related to security threats and regulatory issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

principalColumn

-0.63

 OFDb

-0.59

DidLoad

-0.55

TestTools

-0.54

 zirc

-0.53

 Impressions

-0.52

ngOnDestroy

-0.51

ArgsConstructor

-0.51

Gön

-0.51

Autoritní

-0.50

POSITIVE LOGITS

 warning

2.04

 alarm

2.02

 alert

1.93

 warnings

1.81

 warn

1.76

 alerts

1.75

 Alert

1.73

 alarms

1.73

 Warning

1.71

 Alarm

1.69

Activations Density 0.216%

alerts and warnings related to security threats and regulatory issues

No Comments

No Known Activations