INDEX

Explanations

terms related to healthcare professions and specialties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SharedDtor

-0.81

ismet

-0.70

 SIMBAD

-0.68

Soorten

-0.66

principalTable

-0.64

urlpatterns

-0.63

ότη

-0.63

 Rooney

-0.62

 serializers

-0.61

 Atari

-0.60

POSITIVE LOGITS

 تانيه

0.67

monary

0.60

opedic

0.60

 ophthal

0.59

)$/,

0.54

paedic

0.52

ContentAsync

0.52

 orthopedic

0.51

 neuros

0.51

 oncology

0.49

Activations Density 0.518%

terms related to healthcare professions and specialties

No Comments

No Known Activations