INDEX

Explanations

references to academic journal articles and publications

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

–

-0.45

itatea

-0.45

 wait

-0.41

or

-0.41

wait

-0.40

Wait

-0.39

les

-0.39

-0.38

 nightlife

-0.38

at

-0.37

POSITIVE LOGITS

########.

0.95

featureID

0.81

 kasarigan

0.80

IUrlHelper

0.78

Efq

0.77

 Cæsar

0.77

brtc

0.76

rhosis

0.75

PhysRev

0.75

AndroidJUnit

0.74

Activations Density 0.142%

references to academic journal articles and publications

No Comments

No Known Activations