INDEX

Explanations

phrases indicating quantitative relationships and comparisons

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

 Heath

-0.46

 Extragalactic

-0.45

 mxArray

-0.45

PrototypeOf

-0.45

多种

-0.44

*/].

-0.44

Cannot

-0.43

 порядке

-0.43

adget

-0.42

diging

-0.42

POSITIVE LOGITS

GEBURTSDATUM

0.86

ThroughAttribute

0.71

出版年

0.69

 loudest

0.64

 brunt

0.62

 heaviest

0.62

 estekak

0.61

WebServlet

0.61

Vidite

0.58

/**

0.58

Activations Density 0.346%

phrases indicating quantitative relationships and comparisons

No Comments

No Known Activations