INDEX

Explanations

phrases indicating possession or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Majefty

-1.51

 itſelf

-1.44

 himſelf

-1.42

 myſelf

-1.41

 fubject

-1.25

 Monfieur

-1.25

 themſelves

-1.22

Efq

-1.22

 Houſe

-1.21

 neceff

-1.20

POSITIVE LOGITS

0.95

the

0.91

 time

0.83

“

0.81

 Time

0.70

The

0.70

an

0.69

 difficult

0.68

0.67

Activations Density 0.216%

phrases indicating possession or relationships

No Comments

No Known Activations