INDEX

Explanations

mathematical proofs and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

tvguidetime

-0.60

rrggbb

-0.60

 Hari

-0.57

Cry

-0.56

Hir

-0.54

ʒ

-0.54

 Vill

-0.52

تك

-0.52

 Golden

-0.52

epam

-0.52

POSITIVE LOGITS

 صوتيه

0.71

HostException

0.69

 مواليد

0.64

enderror

0.64

 isolado

0.63

holdet

0.63

StoryboardSegue

0.63

eseorang

0.62

InjectAttribute

0.62

 følgende

0.61

Activations Density 0.252%

mathematical proofs and arguments

No Comments

No Known Activations