INDEX

Explanations

phrases related to healthcare and clinical settings

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

hospital reputation

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

NameInMap

-0.54

 autorytatywna

-0.54

 ligiloj

-0.46

vician

-0.42



-0.42

 مرئيه

-0.41

SBATCH

-0.39

RegressionTest

-0.39

ioutil

-0.38

ModelMap

-0.37

POSITIVE LOGITS

 وتسجيلات

0.66

 ControllerBase

0.50

 physio

0.46

Ris

0.46

 phys

0.45

 mortar

0.44

Ec

0.43

Phy

0.43

!***

0.42

Rol

0.41

Activations Density 0.108%

phrases related to healthcare and clinical settings

hospital reputation

No Comments

No Known Activations