INDEX

Explanations

instances where specific subjects or entities are mentioned within the text

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

 intptr

-0.54

MLLoader

-0.53

ppur

-0.48

HasForeignKey

-0.48

utenants

-0.47

 wikipagina

-0.47

Примечание

-0.46

appré

-0.45

 usah

-0.45

 parkir

-0.45

POSITIVE LOGITS

 تضيفلها

1.04

脚注の使い方

0.77

RenderAtEndOf

0.73

adaptiveStyles

0.72

UnusedPrivate

0.70

BeginContext

0.67

 насељу

0.66

 defaultstate

0.65

mybatisplus

0.64

yntaxException

0.64

Activations Density 0.108%

instances where specific subjects or entities are mentioned within the text

No Comments

No Known Activations