INDEX

Explanations

markers or symbols associated with code or programming functions

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

 ExecuteAsync

-0.53

CancelButton

-0.50

par

-0.47

TouchEvent

-0.46

parente

-0.46

ostro

-0.46

or

-0.46

katu

-0.46

onghi

-0.45

quine

-0.43

POSITIVE LOGITS

ValueStyle

0.89

UserScript

0.81

 jspb

0.78

 linkovi

0.76

 Waray

0.73

IntoConstraints

0.72

RegressionTest

0.72

 NUKAT

0.72

 estekak

0.71

 estimés

0.71

Activations Density 0.349%

markers or symbols associated with code or programming functions

No Comments

No Known Activations