INDEX

Explanations

expressions of conflict or dispute in personal or professional interactions

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

Negative reviews or warnings

np_acts-logits-general · gemini-2.0-flash

beware of scams and bad service

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WHM

-0.47

 peran

-0.47

écuter

-0.43

softc

-0.43

мум

-0.43

 essais

-0.43

 aceptación

-0.42

 assuré

-0.42

줬

-0.42

 INVENTION

-0.41

POSITIVE LOGITS

 beware

0.74

Scam

0.73

ArrowToggle

0.73

 Beware

0.71

 scammed

0.70

Beware

0.68

被害

0.67

 suing

0.66

 retaliation

0.66

 venge

0.65

Activations Density 0.185%

expressions of conflict or dispute in personal or professional interactions

Negative reviews or warnings

beware of scams and bad service

No Comments

No Known Activations