INDEX

Explanations

references to sections, papers, or citations within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 jsPsych

-0.56

CppCodeGen

-0.51

ftagPool

-0.46

 iſt

-0.46

prefixer

-0.45

ValueStyle

-0.44

Искәрмәләр

-0.44

 autorytatywna

-0.44

 outputStream

-0.44

BASEPATH

-0.43

POSITIVE LOGITS

 imprensa

0.48

figured

0.45

contentLoaded

0.43

})).

0.40

 televisão

0.40

 specchio

0.40

acamata

0.39

 kirj

0.39

 publicação

0.39

--)

0.38

Activations Density 0.993%

references to sections, papers, or citations within a document

No Comments

No Known Activations