INDEX

Explanations

technical terms related to programming and system configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

NameInMap

-0.60

 propOrder

-0.47

 ModelExpression

-0.41

ervos

-0.41

insics

-0.41

MigrationBuilder

-0.40

 kasarigan

-0.38

OGND

-0.38

 useCallback

-0.37

 viewDidLoad

-0.37

POSITIVE LOGITS

UrlResolution

0.51

 rerun

0.51

FormTagHelper

0.51

 script

0.49

 scripts

0.48

sidemargin

0.48

 Scripts

0.46

AnchorTagHelper

0.46

run

0.46

runApp

0.45

Activations Density 0.508%

technical terms related to programming and system configuration

No Comments

No Known Activations