INDEX

Explanations

statistical references and discussions related to clinical studies or results

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

values following "stat"

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

 '-';

-0.60

Tembelea

-0.57

 IconData

-0.54

]")]

-0.53

 Italijanski

-0.52

 kohdetta

-0.51

oredCriteria

-0.49

 Roskov

-0.49

Descripció

-0.49

 /\.(

-0.49

POSITIVE LOGITS

twimg

0.38

Datuak

0.37

hang

0.32

󠁢

0.32

 pluie

0.32

useNewUrlParser

0.32

Jeez

0.31

łaś

0.31

 obligé

0.31

ldr

0.30

Activations Density 0.075%

statistical references and discussions related to clinical studies or results

values following "stat"

No Comments

No Known Activations