INDEX

Explanations

technical terms and references related to game development and programming constructs

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

PerformLayout

-0.43

脚注の使い方

-0.40

日閲覧

-0.37

 gynhyrchwyd

-0.37

=$?

-0.36

*/].

-0.36

httphttps

-0.35

ArgsConstructor

-0.35

writerow

-0.33

writeFieldEnd

-0.33

POSITIVE LOGITS

ⓧ

0.57

 invokingState

0.54

 Numerade

0.51

 Remark

0.50

 lenker

0.50

 Plural

0.50

rollment

0.49

Попис

0.48

yelitis

0.48

 Corbett

0.47

Activations Density 0.693%

technical terms and references related to game development and programming constructs

No Comments

No Known Activations