INDEX

Explanations

phrases that indicate methods or ways of achieving something

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

 obedience

-0.57

ScopeManager

-0.56

 Mahogany

-0.53

 leprosy

-0.49

 allergies

-0.49

 viewDidLoad

-0.49

 menopause

-0.49

Derp

-0.48

jęcie

-0.48

 infarction

-0.48

POSITIVE LOGITS

webElementXpaths

0.80

 ways

0.78

 Ways

0.77

Ways

0.73

 WAYS

0.68

цездатний

0.66

djangoproject

0.64

transQ

0.63

richTextPanel

0.62

ngrx

0.60

Activations Density 0.155%

phrases that indicate methods or ways of achieving something

No Comments

No Known Activations