INDEX

Explanations

conjunctions that indicate connections or relationships between ideas

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

transQ

-0.61

یرات

-0.57

 خلاف

-0.56

 mastered

-0.55

 yaptı

-0.54

 coached

-0.52

 handled

-0.52

 parseFrom

-0.52

 знал

-0.52

 betweenstory

-0.51

POSITIVE LOGITS

enumi

0.85

脚注の使い方

0.72

archiviato

0.71

\{\\

0.69

 Pingback

0.65

ItemGroup

0.64

 BoxFit

0.63

yanka

0.63

 nawr

0.63

 Truy

0.62

Activations Density 0.254%

conjunctions that indicate connections or relationships between ideas

No Comments

No Known Activations

conjunctions that indicate connections or relationships between ideas

No Comments

No Known Activations