INDEX

Explanations

phrases indicating relationships or connections between entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 double

-0.49

 Chio

-0.48

 Sagar

-0.44

انيا

-0.44

ตร์

-0.42

 chio

-0.42

יק

-0.41

nell

-0.41

 also

-0.41

 doble

-0.40

POSITIVE LOGITS

 onBind

0.82

getRuntime

0.80

TypedDataSet

0.80

الإنجليزية

0.79

RenderAtEndOf

0.77

JspWriter

0.73

TintMode

0.73

Obrázky

0.69

 متعلقه

0.69

felves

0.68

Activations Density 0.281%

phrases indicating relationships or connections between entities or concepts

No Comments

No Known Activations