INDEX

Explanations

terms related to lodging and accommodations

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

near or related to hotels

np_acts-logits-general · gemini-2.0-flash

hotel

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

RenderAtEndOf

-0.69

 ddelweddau

-0.67

 autorytatywna

-0.66

 &___

-0.62

tonode

-0.59

saraba

-0.57

Autoritní

-0.57

 AttributeSet

-0.57

astéroïdes

-0.55

MessageTagHelper

-0.54

POSITIVE LOGITS

 hotel

1.72

 hotels

1.57

 Hotel

1.44

Hotel

1.40

hotel

1.40

 Hotels

1.36

 HOTEL

1.27

hotels

1.25

 hote

1.20

Hotels

1.20

Activations Density 0.185%

terms related to lodging and accommodations

near or related to hotels

hotel

No Comments

No Known Activations