INDEX

Explanations

references and discussions related to performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 فريبيس

-1.13

RenderAtEndOf

-0.86

SequentialGroup

-0.77

 BoxFit

-0.75

AsUp

-0.73

 kaynağından

-0.72

HasAnnotation

-0.71

yntaxException

-0.71

 Geduld

-0.70

 navideños

-0.68

POSITIVE LOGITS

 performances

0.94

Performances

0.92

 PERFORM

0.88

 Performances

0.86

 perform

0.84

 Perform

0.82

Perform

0.81

 performers

0.76

 performing

0.75

perform

0.75

Activations Density 0.136%

references and discussions related to performance metrics

No Comments

No Known Activations