INDEX

Explanations

terms related to biological measurements and medical imaging techniques

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 referenties

-0.65

sidemargin

-0.63

Tikang

-0.58

GeoNames

-0.54

bootstrapcdn

-0.53

 cliquer

-0.53

kasse

-0.53

اریخ

-0.52

 téléph

-0.52

 commerciaux

-0.52

POSITIVE LOGITS

 including

0.73

romolecules

0.65

 ModelExpression

0.60

 facilities

0.59

 Réponses

0.59

})));

0.59

including

0.58

 resources

0.57

 entities

0.57

 objects

0.57

Activations Density 1.783%

terms related to biological measurements and medical imaging techniques

No Comments

No Known Activations