INDEX

Explanations

structured data elements, specifically those related to programming definitions and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

RenderAtEndOf

-0.76

 ligiloj

-0.69

 autorytatywna

-0.69

 متعلقه

-0.59

 للمعارف

-0.59

 estekak

-0.59

 poveznice

-0.55

 nakalista

-0.54

LikeLike

-0.53

Искәрмәләр

-0.53

POSITIVE LOGITS

EDEFAULT

0.63

ljeno

0.59

orsese

0.57

formik

0.57

Composable

0.54

ptonshire

0.53

edema

0.52

\{\\

0.51

 CommonModule

0.51

IntoConstraints

0.50

Activations Density 0.135%

structured data elements, specifically those related to programming definitions and attributes

No Comments

No Known Activations