INDEX

Explanations

expressions indicating possession or receipt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ویکی‌پدیا

-0.63

MimeType

-0.57

pins

-0.51

üğ

-0.51

ismet

-0.50

its

-0.48

Tags

-0.47

interna

-0.47

Bains

-0.46

rins

-0.45

POSITIVE LOGITS

 themselves

1.56

themselves

1.31

Their

1.28

 Their

1.25

 their

1.19

 THEIR

1.18

their

1.01

 they

0.99

 Leur

0.98

 They

0.95

Activations Density 0.286%

expressions indicating possession or receipt

No Comments

No Known Activations