INDEX

Explanations

sections that indicate categorization or tagging of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ứng

-0.64

 simplifié

-0.58

 primit

-0.57

polazione

-0.56

-0.55

brainly

-0.54

 Mérimée

-0.54

 GenerationType

-0.53

 Protección

-0.53

Filmografia

-0.52

POSITIVE LOGITS

 Uncategorized

0.57

}`,

0.56

TagMode

0.56

mord

0.52

 cruc

0.52

 écl

0.51

 لينك

0.51

})*/

0.49

وضوع

0.49

*',

0.49

Activations Density 0.101%

sections that indicate categorization or tagging of content

No Comments

No Known Activations