INDEX

Explanations

references to harassment and threatening behavior in the workplace

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

Harassment, threats, or intimidation

np_acts-logits-general · gemini-2.0-flash

physically threatening and harassment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 kıs

-0.34

 camuf

-0.34

 oportunidad

-0.34

 oportunidade

-0.33

nai

-0.33

hí

-0.33

 scopri

-0.32

 uParam

-0.32

 aggi

-0.32

 provved

-0.32

POSITIVE LOGITS

 harassing

0.79

 harassment

0.79

 threatening

0.77

 threats

0.76

 intimidation

0.73

 intimidate

0.72

 intimidating

0.72

Threats

0.71

 Harassment

0.70

 harass

0.68

Activations Density 0.408%

references to harassment and threatening behavior in the workplace

Harassment, threats, or intimidation

physically threatening and harassment

No Comments

No Known Activations