INDEX

Explanations

phrases related to reporting incidents to authorities or seeking help, particularly in the context of crime, harassment, or safety concerns.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

information regarding legal issues or cases.

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

descriptions of physical attributes and information about individuals.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

Reporting an incident or problem

np_acts-logits-general · gemini-2.0-flash

reporting issues or complaints

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ujednoznacz

-0.68

InSection

-0.67

RegressionTest

-0.66

saraba

-0.60

AsUp

-0.59

 CreateTagHelper

-0.59

 विश्वसनीयता

-0.58

帖最后由

-0.57

!*\

-0.55

 calendriers

-0.55

POSITIVE LOGITS

 reporting

2.25

 report

2.19

 reported

2.05

 Report

1.98

 Reporting

1.97

Report

1.97

report

1.96

 reports

1.93

 REPORT

1.88

REPORT

1.87

Activations Density 0.344%