INDEX

Explanations

references to companies, organizations, or groups in a business context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 étrangère

-0.73

 religieuses

-0.65

 esimer

-0.64

 kysy

-0.60

 Савезне

-0.57

 fewest

-0.57

 scolaires

-0.57

 Pingback

-0.57

Gambas

-0.57

 esempi

-0.57

POSITIVE LOGITS

typeorm

0.69

énario

0.67

0.66

’

0.65

ollectionView

0.63

SharedCtor

0.60

 مشين

0.59

TagHelpers

0.59

coroutines

0.59

 viewDidLoad

0.57

Activations Density 0.486%

references to companies, organizations, or groups in a business context

No Comments

No Known Activations