INDEX

Explanations

scientific terms and measurements related to study results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

̍t

-0.49

 Juga

-0.48

LEn

-0.45

☰

-0.44

enumi

-0.44

 vuel

-0.43

spyOn

-0.42

Referencie

-0.42

Lähteet

-0.42

apl

-0.41

POSITIVE LOGITS

 Normdatei

0.78

)»

0.70

結果は

0.57

 Saltar

0.56

 RSSSF

0.55

],"

0.54

 ***!

0.52

 averages

0.52

 оказалось

0.52

 privilégi

0.52

Activations Density 1.847%

scientific terms and measurements related to study results

No Comments

No Known Activations