INDEX

Explanations

phrases related to product reviews and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

withIdentifier

-0.63

lusconi

-0.62

出版年

-0.60

انيف

-0.60

onOptions

-0.59

NamedQuery

-0.59

NamedQueries

-0.59

orexia

-0.57

birthDate

-0.57

RectangleBorder

-0.57

POSITIVE LOGITS

 test

0.70

test

0.68

 testing

0.67

 testers

0.63

 tested

0.63

Test

0.61

 review

0.59

 Test

0.57

 tester

0.57

 тесто

0.56

Activations Density 0.139%

phrases related to product reviews and evaluations

No Comments

No Known Activations