INDEX

Explanations

references to weight and mass characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 للمعارف

-0.65

Hochspringen

-0.64

 مشارکت‌کنندگان

-0.58

limard

-0.58

 كومونز

-0.57

 ovation

-0.56

 snippetHide

-0.55

acherous

-0.54

toHaveBeen

-0.54

xito

-0.53

POSITIVE LOGITS

 weight

1.45

weight

1.29

 Weight

1.25

 weigh

1.24

 WEIGHT

1.24

Weight

1.23

 weights

1.21

 weighing

1.21

WEIGHT

1.18

 weighs

1.15

Activations Density 0.307%

references to weight and mass characteristics

No Comments

No Known Activations