INDEX

Explanations

descriptions related to visual appearance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 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

 CanadaChoose

-0.70

EndProject

-0.66

Controllo

-0.64

"){

-0.59

 Czer

-0.59

viation

-0.58

supset

-0.58

});*/

-0.58

 Mand

-0.58

//

-0.58

POSITIVE LOGITS

looks

1.03

 Looks

1.02

Looks

1.00

 looks

1.00

 appear

0.88

 sounded

0.84

 APPE

0.83

 looked

0.83

 LOOKS

0.82

 dirait

0.82

Activations Density 0.148%

descriptions related to visual appearance

No Comments

No Known Activations