INDEX

Explanations

references to UTF encoding and charset definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 onBind

-0.50

disposing

-0.49

cdk

-0.48

$_['

-0.46

WithIOException

-0.44

featureID

-0.43

getColumnIndex

-0.41

typeorm

-0.41

getDescriptor

-0.41

sizeCache

-0.41

POSITIVE LOGITS

UTF

0.57

utf

0.56

UTF

0.56

 ProtoMessage

0.52

ViewFeatures

0.49

utf

0.48

########.

0.48

ChildScrollView

0.45

interopRequire

0.45

 wireType

0.44

Activations Density 0.153%

references to UTF encoding and charset definitions

No Comments

No Known Activations