INDEX

Explanations

terms related to technical specifications and system features for performance evaluation

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

 sogni

-0.63

olingo

-0.61

 noDo

-0.60

ziasztok

-0.56

romptu

-0.56

Spécification

-0.56

 pouvoit

-0.56

 betweenstory

-0.55

enfone

-0.55

 aigu

-0.55

POSITIVE LOGITS

 patented

0.82

 improved

0.82

 proprietary

0.81

 innovative

0.76

 technology

0.76

 innovation

0.72

独自の

0.69

 innov

0.69

 PATENT

0.68

 pioneered

0.68

Activations Density 0.357%

terms related to technical specifications and system features for performance evaluation

No Comments

No Known Activations