INDEX

Explanations

characters and symbols used in coding or digital representations

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

gev

-0.59

Aholisi

-0.48

TagMode

-0.47

 Италијани

-0.47

ScopeManager

-0.44

Diweddarwch

-0.43

RenderAtEndOf

-0.42

hake

-0.42

 Bowers

-0.42

neté

-0.42

POSITIVE LOGITS

omiast

0.41

 gynnwys

0.40

 kişinin

0.40

 çift

0.39

 Olsson

0.38

 końca

0.38

siyon

0.38

 clientId

0.37

eseorang

0.36

 imageUrl

0.35

Activations Density 0.666%

characters and symbols used in coding or digital representations

No Comments

No Known Activations