INDEX

Explanations

terms related to usage, actions, and efforts

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

 olyan

-0.59

 such

-0.56

bebasan

-0.54

 Such

-0.53

 some

-0.52

 your

-0.50

wie

-0.49

my

-0.48

 alia

-0.48

such

-0.48

POSITIVE LOGITS

Хьажоргаш

0.80

 ―――――

0.79

 himſelf

0.77

 NDEBUG

0.70

Efq

0.69

 itſelf

0.68

 Monfieur

0.67

UpdateCommand

0.67

 myſelf

0.66

EventEmitter

0.66

Activations Density 0.599%

terms related to usage, actions, and efforts

No Comments

No Known Activations