INDEX

Explanations

concepts and evaluations related to healthcare interventions and their effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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



-0.73

🏻

-0.52

 youngest

-0.52

});*/

-0.51

 الاطلاع

-0.51

Efq

-0.51

Begriffsklä

-0.50

//});

-0.50

 متحده

-0.49

 caro

-0.48

POSITIVE LOGITS

这类

0.88

 ilyen

0.74

 kän

0.69

 solcher

0.69

 these

0.68

 such

0.66

 Такие

0.65

 takim

0.63

 solchen

0.63

these

0.62

Activations Density 0.672%

concepts and evaluations related to healthcare interventions and their effectiveness

No Comments

No Known Activations