INDEX

Explanations

terms and phrases related to organizational structures and business operations

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

Follows nouns

np_acts-logits-general · gemini-2.0-flash

services and items

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

 customizable

-0.69

 flavorful

-0.67

 farther

-0.67

AVOR

-0.67

 harbor

-0.66

 esposo

-0.64

 customize

-0.64

enggarakan

-0.63

 harbors

-0.62

Tembelea

-0.62

POSITIVE LOGITS

–

0.83

0.82

 which

0.79

 iaitu

0.78

 whilst

0.76

 Whilst

0.71

Whilst

0.70

Välislingid

0.60

(£

0.58

 programme

0.58

Activations Density 0.536%

terms and phrases related to organizational structures and business operations

Follows nouns

services and items

No Comments

No Known Activations