INDEX

Explanations

terms associated with abuse and derogatory behavior

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

abusive, oppressive, toxic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

viewDidLoad

-0.54

 ujednoznacz

-0.54

 recreation

-0.49

hasMoreElements

-0.49

 regola

-0.46

Recommendation

-0.46

rscheinlichkeit

-0.46

MeasureSpec

-0.46

SerializeField

-0.46

Recreation

-0.46

POSITIVE LOGITS

 abusive

1.66

 abusi

0.98

 oppressive

0.84

 toxic

0.70

 abuser

0.66

 Toxic

0.65

 Aggressive

0.65

abu

0.65

 predatory

0.65

Aggressive

0.62

Activations Density 0.014%

terms associated with abuse and derogatory behavior

abusive, oppressive, toxic

No Comments

No Known Activations