INDEX

Explanations

discussions about providing information or details, particularly in a context of communication or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

openConnection

-0.57

 continúas

-0.57

ølge

-0.52

">//

-0.48

sidemargin

-0.48

亥

-0.47

tawesome

-0.47

argout

-0.46

λίου

-0.44

jock

-0.44

POSITIVE LOGITS

kloped

0.71

annica

0.68

enumi

0.61

 الرياضيه

0.61

 filtres

0.59

omock

0.58

 tungkol

0.57

RefNanny

0.55

ModelAdmin

0.55

URIComponent

0.55

Activations Density 0.322%

discussions about providing information or details, particularly in a context of communication or explanations

No Comments

No Known Activations