INDEX

Explanations

specific details about products and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

UserScript

-0.87

 يتيمه

-0.82

出版年

-0.63

XmlAccessType

-0.61

});*/

-0.61

 Dlatego

-0.60

 circumstance

-0.60

BarButtonItem

-0.60

 circumstances

-0.60

Vidite

-0.60

POSITIVE LOGITS

 Vielzahl

0.61

abundance

0.58

 large

0.56

 variety

0.55

mix

0.54

 assortment

0.54

 Waray

0.54

variety

0.53

 touch

0.52

 abundance

0.51

Activations Density 0.326%

specific details about products and features

No Comments

No Known Activations