INDEX

Explanations

references to living spaces or home environments

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

"living room" co-occurrences

np_acts-logits-general · gemini-2.0-flash

living room

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

DockStyle

-0.96

 дописавши

-0.96

 ब्रेकडाउन

-0.82

存于互联网档案馆

-0.75

swire

-0.71

 BoxFit

-0.69

 pinulongan

-0.69

发表于

-0.67

 تضيفلها

-0.65

RectangleBorder

-0.65

POSITIVE LOGITS

 room

1.24

room

1.19

 Room

1.02

 area

0.98

Room

0.93

 ROOM

0.87

area

0.80

 areas

0.80

 Area

0.76

ROOM

0.71

Activations Density 0.077%

references to living spaces or home environments

"living room" co-occurrences

living room

No Comments

No Known Activations