INDEX

Explanations

elements or tags in markup languages like HTML and XML

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Allociné

-0.50

 censorship

-0.47

 double

-0.46

AFR

-0.46

 absorber

-0.45

 Meksiku

-0.45

 dancing

-0.44

anda

-0.44

hor

-0.43

iken

-0.43

POSITIVE LOGITS

Autoritní

0.68

Gambas

0.64

berdayakan

0.63

Personendaten

0.62

 couvercle

0.59

WaitGroup

0.59

 tartalomajánló

0.59

 rowspan

0.58

 âmes

0.57

,<

0.57

Activations Density 0.060%

elements or tags in markup languages like HTML and XML

No Comments

No Known Activations