INDEX

Explanations

numerical data or statistical results

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

EditorBrowsable

-0.66

 createState

-0.54

 useState

-0.52

GroupLayout

-0.52

useState

-0.51

 propOrder

-0.50

 XMLHttpRequest

-0.50

ennheiser

-0.49

 Basin

-0.48

帖最后由

-0.47

POSITIVE LOGITS

tagHelperRunner

0.85

出版年

0.77

Autoritní

0.65

 lenker

0.64

 صوتيه

0.57

 незавершена

0.54

ScopeManager

0.53

iformis

0.53

 bénéfice

0.53

Diweddarwch

0.52

Activations Density 0.141%

numerical data or statistical results

No Comments

No Known Activations