INDEX

Explanations

terms and concepts related to medical education and specialties, particularly in neurology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Picchu

-0.71

hamma

-0.64

 spro

-0.63

piration

-0.62

 sprocket

-0.62

 AssemblyCulture

-0.61

ositol

-0.60

 Krav

-0.59

 Propriété

-0.58

vige

-0.58

POSITIVE LOGITS

 specialties

0.74

 specialty

0.72

 specialist

0.70

Specialist

0.61

 speciality

0.59

 specialists

0.59

Aholisi

0.59

specialist

0.58

specialty

0.58

 especialista

0.55

Activations Density 0.198%

terms and concepts related to medical education and specialties, particularly in neurology

No Comments

No Known Activations