INDEX

Explanations

references to office environments and related terminology

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

following "office" or "Office"

np_acts-logits-general · gemini-2.0-flash

office followed by a related noun

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tembelea

-0.85

TagMode

-0.83

✨:

-0.72

 تضيفلها

-0.71

 Catan

-0.70

adays

-0.70

 Kunt

-0.70

 transférez

-0.69

notated

-0.68

IntoConstraints

-0.67

POSITIVE LOGITS

 offices

1.39

 office

1.36

 Office

1.30

 OFFICE

1.26

office

1.23

 Offices

1.20

Office

1.19

OFFICE

1.11

 Büro

1.10

 OFFICES

1.09

Activations Density 0.074%

references to office environments and related terminology

following "office" or "Office"

office followed by a related noun

No Comments

No Known Activations