INDEX

Explanations

mathematical operations involving rounding and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 setId

-0.60

 faveur

-0.54

tute

-0.51

anguard

-0.50

elter

-0.48

RenderAtEndOf

-0.47

ειτουργ

-0.46

setLayoutParams

-0.46

offsetHeight

-0.45

angu

-0.45

POSITIVE LOGITS

 rounding

1.25

 precision

1.24

 accuracy

1.23

 rounded

1.13

precision

1.03

 Precision

1.03

 round

1.03

 Round

1.01

Precision

1.00

 decimals

0.99

Activations Density 0.264%

mathematical operations involving rounding and numerical values

No Comments

No Known Activations