INDEX

Explanations

references to prominent public figures or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 الرياضيه

-0.48

 Darlington

-0.43

unknownFields

-0.43

 oprot

-0.42

pantalones

-0.41

الحياه

-0.41

 unſ

-0.41

IGENCE

-0.40

ंदीखरीदारी

-0.40

dersfield

-0.39

POSITIVE LOGITS

AddTagHelper

0.40

 Référence

0.38

SOUNDBITE

0.35

 rencontré

0.35

图为

0.35

MigrationBuilder

0.34

 defaultstate

0.34

 ferons

0.34

 recevrez

0.33

Przypisy

0.33

Activations Density 0.198%

references to prominent public figures or events

No Comments

No Known Activations