INDEX

Explanations

technical terms and identifiers used in programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

featureID

-0.50

Personendaten

-0.47

цездатний

-0.44

ItemBackground

-0.44

GOTREF

-0.42

 kasarigan

-0.41

ChildScrollView

-0.41

postsleuth

-0.41

-0.40

kyou

-0.40

POSITIVE LOGITS

GTCX

0.48

 CreateTagHelper

0.46

↹

0.41

IntoConstraints

0.40

 channel

0.40

лтамалар

0.39

 ویکی‌پدی

0.38

 prioriti

0.38

tinyos

0.38

dė

0.38

Activations Density 0.692%

technical terms and identifiers used in programming or coding contexts

No Comments

No Known Activations