INDEX

Explanations

references to devices and their characteristics in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Weblinks

-0.94

 InputDecoration

-0.92

 sopr

-0.88

 ujednoznacz

-0.81

endphp

-0.76

 kysy

-0.76

Glorious

-0.75

withstanding

-0.74

rophobic

-0.73

?}",

-0.72

POSITIVE LOGITS

 devices

1.94

 device

1.85

 Devices

1.68

devices

1.67

 Device

1.67

 DEVICE

1.59

Device

1.57

device

1.57

DEVICE

1.52

 DEVICES

1.51

Activations Density 0.075%

references to devices and their characteristics in technical contexts

No Comments

No Known Activations