INDEX

Explanations

references to various scientific constants and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

Inflater

-0.84

arrings

-0.81

GEBURTSDATUM

-0.75

 mắn

-0.73

 SDLK

-0.70

StoreMessageInfo

-0.69

Geplaatst

-0.69

Portail

-0.68

}))

-0.67

saraba

-0.66

POSITIVE LOGITS

 getC

0.79

getC

0.79

 Cougars

0.69

CQ

0.67

 Cary

0.66

Cs

0.65

cupertino

0.64

CDA

0.63

CNA

0.62

classnames

0.60

Activations Density 0.882%

references to various scientific constants and parameters

No Comments

No Known Activations