INDEX

Explanations

technical terms related to robust statistical analysis and financial models

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

robustness, filtering, agreement, spectrum disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Wikimedijinoj

-0.64

findpost

-0.64

EDEFAULT

-0.59

RegistryLite

-0.59

Hozzáférés

-0.56

KommentareTeilen

-0.56

WebVitals

-0.55

HasAnnotation

-0.55

InitVars

-0.54

BufferException

-0.54

POSITIVE LOGITS

 curé

0.35

 cimetière

0.32

 ferons

0.32

 nuage

0.31

 Италијани

0.30

↵↵

0.30

</h2>

0.29

฿

0.29

rajz

0.29

↵

0.28

Activations Density 0.008%

technical terms related to robust statistical analysis and financial models

robustness, filtering, agreement, spectrum disorders

No Comments

No Known Activations