INDEX

Explanations

words and phrases related to hypothetical situations and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 pleaſure

-0.80

 RoutedEventArgs

-0.75

 houſe

-0.71

 ―――――

-0.68

ollectionView

-0.68

tvguidetime

-0.67

 NgModule

-0.67

 SafeMath

-0.66

roe

-0.66

 ſtate

-0.66

POSITIVE LOGITS

 else

0.64

 otherwise

0.61

 oder

0.55

 Alternatively

0.51

per

0.51

too

0.50

Otherwise

0.50

δη

0.49

otherwise

0.49

Pan

0.48

Activations Density 0.222%

words and phrases related to hypothetical situations and inquiries

No Comments

No Known Activations