INDEX

Explanations

references to various organs and their conditions within scientific or medical contexts

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

status or condition of organs

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

')):

-0.50

 Esco

-0.46

 Lari

-0.45

 Prescott

-0.44

embre

-0.43

}~

-0.43

 Fré

-0.43

::$

-0.42

 Santa

-0.42

Esti

-0.42

POSITIVE LOGITS

 organs

1.65

 Organs

1.58

 organ

1.54

 órganos

1.38

 organes

1.38

 órgano

1.23

 órgãos

1.20

器官

1.15

 órg

1.12

organe

0.98

Activations Density 0.005%

references to various organs and their conditions within scientific or medical contexts

status or condition of organs

No Comments

No Known Activations