INDEX

Explanations

references to data structures, class definitions, and programming methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

kuuta

-0.72

EntityFramework

-0.51

removeAll

-0.50

ItemBackground

-0.50

EndGlobalSection

-0.48

Personensuche

-0.47

windowFixed

-0.47

awtextra

-0.46

énario

-0.46

men

-0.46

POSITIVE LOGITS

appartamento

0.63

 OnTrigger

0.57

 Svar

0.55

 ویکی‌پدیا

0.54

ſelves

0.52

 }}$}

0.52

 épis

0.52

……"

0.51

 Ganes

0.51

Bris

0.50

Activations Density 0.043%

references to data structures, class definitions, and programming methodologies

No Comments

No Known Activations