INDEX

Explanations

terms and phrases related to health, diagnostics, and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

IsContent

-0.60

BibitemShut

-0.58

 arşivlendi

-0.57

httphttps

-0.56

Sådan

-0.52

 atmósfera

-0.52

 sécurisé

-0.51

bibinfo

-0.50

 visibilidad

-0.50

 AssemblyCompany

-0.49

POSITIVE LOGITS

WriteTagHelper

0.34

OK

0.32

Espèce

0.30

 phan

0.30

Forms

0.30

 form

0.29

ok

0.28

 Baba

0.28

Facades

0.28

lib

0.28

Activations Density 0.928%

terms and phrases related to health, diagnostics, and medical conditions

No Comments

No Known Activations