INDEX

Explanations

references to licenses and identification documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 mxArray

-0.78

 تضيفلها

-0.63

 kasarigan

-0.63

국의

-0.61

 createSprite

-0.58

 createStore

-0.57

étape

-0.57

 geslacht

-0.53

êque

-0.52

thenia

-0.52

POSITIVE LOGITS

المراجع

0.71

 Reſ

0.69

 AppColors

0.69

談社

0.69

JIT

0.66

 Inſ

0.65

+:+

0.65

},[])

0.64

期刊论文

0.63

原始内容存档于

0.62

Activations Density 0.239%

references to licenses and identification documents

No Comments

No Known Activations

references to licenses and identification documents

No Comments

No Known Activations