INDEX

Explanations

specific product names and categories in retail contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-1.02

Personendaten

-0.82

 disambiguazione

-0.71

 للمعارف

-0.64

المناصب

-0.64

 newOwner

-0.63

 سكانية

-0.60

 BoxFit

-0.60

mpagne

-0.60

StartTag

-0.59

POSITIVE LOGITS

__*/

0.36

 Numerade

0.31

artifactId

0.29

 σχέ

0.29

 saisir

0.27

 INTERESAR

0.26

Pyx

0.26

จ

0.25

 carga

0.25

 Akademie

0.25

Activations Density 2.575%

specific product names and categories in retail contexts

No Comments

No Known Activations