INDEX

Explanations

mentions of hotels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

||}

-0.74

WebVitals

-0.72

paksa

-0.70

UnsafeEnabled

-0.70

 Wrench

-0.68

vry

-0.66

 Willen

-0.65

erobic

-0.64

prepareStatement

-0.63

provoking

-0.63

POSITIVE LOGITS

 hotels

1.65

 hotel

1.59

 Hotels

1.49

Hotels

1.46

 Hotel

1.42

hotel

1.41

 HOTEL

1.41

HOTEL

1.35

hotels

1.30

Hotel

1.27

Activations Density 0.003%

mentions of hotels

No Comments

No Known Activations