INDEX

Explanations

occurrences of TODO comments in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

oredCriteria

-0.63

 MongoClient

-0.54

UAGE

-0.53

 Saka

-0.53

Controllo

-0.52

netinet

-0.52

 المعيارى

-0.51

ρων

-0.49

Sair

-0.49

(&:

-0.49

POSITIVE LOGITS

TODO

0.98

 TODO

0.90

曖昧さ回避

0.78

 Infórmanos

0.75

Todo

0.71

todo

0.68

odo

0.65

Toole

0.63

 dolo

0.62

 NOTE

0.61

Activations Density 0.013%

occurrences of TODO comments in the text

No Comments

No Known Activations