INDEX

Explanations

terms related to mathematical assumptions and models in statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

esgue

-0.63

HttpFoundation

-0.63

gonic

-0.62

MIDDLEWARE

-0.60

MethodManager

-0.60

 magasiner

-0.59

 XCTest

-0.58

 <=",

-0.56

scrapy

-0.52

Ẫ

-0.52

POSITIVE LOGITS

 nahilalakip

0.81

 autorytatywna

0.78

</i>

0.57

 تضيفلها

0.54

InstrumentedTest

0.51

Sucesor

0.49

NotFoundError

0.47

</h3>

0.46

Parms

0.46

 continúas

0.45

Activations Density 6.307%

terms related to mathematical assumptions and models in statistics

No Comments

No Known Activations