INDEX

Explanations

specific references to "FL" related terms and expressions, often in the context of a brand or product

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 للمعارف

-0.71

Autoritní

-0.59

findpost

-0.58

 المعيارى

-0.56

 EconPapers

-0.55

 noDo

-0.54

StoryboardSegue

-0.52

 allAfrica

-0.52



-0.51

انجليز

-0.50

POSITIVE LOGITS

fl

0.75

Fl

0.72

FL

0.71

fl

0.63

Fla

0.62

Fl

0.60

Fla

0.58

FL

0.57

fla

0.52

 Фло

0.51

Activations Density 0.181%

specific references to "FL" related terms and expressions, often in the context of a brand or product

No Comments

No Known Activations

specific references to "FL" related terms and expressions, often in the context of a brand or product

No Comments

No Known Activations