INDEX

Explanations

terms related to performance metrics or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

PathVariable

-0.94

InputBorder

-0.92

 kaynağından

-0.91

 فريبيس

-0.90

IonicModule

-0.89

adaptiveStyles

-0.86

yntaxException

-0.84

REDIRECT

-0.84

SequentialGroup

-0.84

 ligiloj

-0.83

POSITIVE LOGITS

 performance

2.61

 performances

2.30

 Performance

2.29

Performance

2.24

performance

2.21

 PERFORMANCE

2.10

PERFORMANCE

2.03

 Performances

1.86

Performances

1.72

perform

1.71

Activations Density 0.089%

terms related to performance metrics or evaluations

No Comments

No Known Activations