INDEX

Explanations

phrases that express relationships or combinations of items, especially using conjunctions and quantifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

펴

-0.53

 katk

-0.52

Примітки

-0.52

SpringRunner

-0.52

}}{

-0.52

))))))))

-0.51

multline

-0.51

ագրություններ

-0.49

neous

-0.48

上記の

-0.48

POSITIVE LOGITS

sizeCache

0.92

Abitanti

0.82

kháu

0.68

fromCharCode

0.66

StoreMessageInfo

0.64

OrEqualTo

0.62

ThemeOverlay

0.62

省市镇

0.62

EndProject

0.61

 <=",

0.60

Activations Density 0.372%

phrases that express relationships or combinations of items, especially using conjunctions and quantifiers

No Comments

No Known Activations