INDEX

Explanations

terms associated with medical testing and health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AddTagHelper

-0.71

ConstraintMaker

-0.66

EndContext

-0.65

SourceChecksum

-0.64

RegistryLite

-0.64

 ligiloj

-0.63

 cherchés

-0.62

 estekak

-0.61

 Biôgrafia

-0.59

تفصیلات

-0.59

POSITIVE LOGITS

 including

0.70

包括

0.55

including

0.54

 features

0.53

 berupa

0.52

cửa

0.51

 anatomy

0.51

 further

0.51

 consisting

0.49

::*;

0.48

Activations Density 0.846%

terms associated with medical testing and health conditions

No Comments

No Known Activations