INDEX

Explanations

statistical measures related to model evaluation and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

Referencies

-0.47

Geplaatst

-0.40

Bakgrunnsstoff

-0.39

 encantan

-0.39

 intptr

-0.37

 debout

-0.35

raquo

-0.33

γραφία

-0.33

 montanha

-0.33

 الاطلاع

-0.33

POSITIVE LOGITS

 accuracy

1.27

 Accuracy

1.09

 precision

1.02

Accuracy

0.96

accuracy

0.96

 Precision

0.93

 recall

0.85

precision

0.84

Precision

0.83

 précision

0.79

Activations Density 1.604%

statistical measures related to model evaluation and performance metrics

No Comments

No Known Activations