INDEX

Explanations

phrases indicating identity, roles, or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 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

DETAILED

-0.40

HasAnnotation

-0.38

 ostavi

-0.36

volatile

-0.34

 chemicals

-0.33

 getItemCount

-0.33

Hentet

-0.33

 Reap

-0.32

calypse

-0.32

έ

-0.32

POSITIVE LOGITS

mybatisplus

0.60

ViewImports

0.57

 فريبيس

0.57

作为一个

0.56

作為

0.54

verwijspagina

0.54

作为

0.54

новништво

0.53

 Sebagai

0.53

 الرياضيه

0.52

Activations Density 0.234%

phrases indicating identity, roles, or relationships

No Comments

No Known Activations