INDEX

Explanations

details about infrastructure and accommodations for people or processes

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

Maximum occupancy or capacity

np_acts-logits-general · gemini-2.0-flash

capacity to seat or hold

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imple

-0.50

="//

-0.49

ImageIO

-0.48

QUALITY

-0.48

➌

-0.48

สือ

-0.48

Quality

-0.46

廉

-0.45

 Volunt

-0.45

esgue

-0.45

POSITIVE LOGITS

 capacity

2.05

 Capacity

1.77

capacity

1.70

 capacities

1.69

Capacity

1.61

 CAPACITY

1.54

 capacidad

1.51

 capacité

1.39

CAPACITY

1.39

 capacidade

1.37

Activations Density 0.124%

details about infrastructure and accommodations for people or processes

Maximum occupancy or capacity

capacity to seat or hold

No Comments

No Known Activations