INDEX

Explanations

key terms and actions related to controls and interfaces in programming and user experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

MarshalTo

-0.48

gql

-0.46

 AspNetCore

-0.45

EnableWeb

-0.44

splatz

-0.44

 CHtml

-0.42

 citizen

-0.42

eu

-0.41

StructEnd

-0.41

MLS

-0.40

POSITIVE LOGITS

posedge

0.49

 estekak

0.49

WireFormatLite

0.49

inSlope

0.47

ToScroll

0.44

enumii

0.42

QMetaType

0.41

expandindo

0.40

increase

0.40

 wireType

0.39

Activations Density 0.432%

key terms and actions related to controls and interfaces in programming and user experience

No Comments

No Known Activations