INDEX

Explanations

terms related to weight and physical characteristics of objects

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

toHaveBeen

-0.52

AndEndTag

-0.51

dike

-0.50

 opening

-0.50

ena

-0.47

出版年

-0.47

τεύ

-0.46

falfa

-0.46

 vulgares

-0.46

getPath

-0.46

POSITIVE LOGITS

 weight

1.32

 weights

1.21

 weighing

1.20

 weighs

1.20

 WEIGHT

1.19

weight

1.18

 weigh

1.16

 Weight

1.15

 heavier

1.13

Weight

1.10

Activations Density 0.205%

terms related to weight and physical characteristics of objects

No Comments

No Known Activations