INDEX

Explanations

references to bottles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 subsidi

-0.55

 Haller

-0.53

grain

-0.48

美味しかったです

-0.48

이

-0.48

 matar

-0.46

pecha

-0.46

cerna

-0.45

 births

-0.45

 tamu

-0.45

POSITIVE LOGITS

 bottle

1.04

 bottles

0.92

 Bottle

0.91

"]);

0.88

ViewFeatures

0.82

 botella

0.81

bottle

0.79

Bottle

0.78

 BOTT

0.78

}],

0.78

Activations Density 0.050%

references to bottles

No Comments

No Known Activations