INDEX

Explanations

terms related to continuous and discrete measurements or observations in statistical models

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

continuous observations or setting

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 FAVOR

-0.35

嫌

-0.34

gnat

-0.31

⇀

-0.31

 fellow

-0.31

Passe

-0.30

 utafitiHapana

-0.30

 sesama

-0.29

хран

-0.29

 substituted

-0.29

POSITIVE LOGITS

 Continuous

1.15

Continuous

1.13

 continuous

1.13

continuous

1.10

 contín

0.91

 continuously

0.88

 continuo

0.84

 kontinuier

0.81

contin

0.80

 Contin

0.79

Activations Density 0.131%

terms related to continuous and discrete measurements or observations in statistical models

continuous observations or setting

No Comments

No Known Activations