INDEX

Explanations

vulgar expressions and profanity

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

awtextra

-0.56

AxisAlignment

-0.48

isuus

-0.48

UIControlState

-0.48

LinkId

-0.46

ihr

-0.44

 ExecuteAsync

-0.44

)?;

-0.42

haviours

-0.42

ológicas

-0.42

POSITIVE LOGITS

 MatDialog

0.76

 outta

0.72

tawesome

0.72

 butterknife

0.70

FUCK

0.67

原始内容存档于

0.67

 Monfieur

0.66

مصادر

0.63

printStackTrace

0.63

urlpatterns

0.62

Activations Density 0.119%

vulgar expressions and profanity

No Comments

No Known Activations