INDEX

Explanations

medical terminology related to treatments and medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WriteTagHelper

-0.69

ArgsConstructor

-0.67

 VizieR

-0.67

раздо

-0.65

 esternos

-0.61

RegistryLite

-0.61

 незавершена

-0.59

 ſche

-0.59

 ſtre

-0.57

 cauſe

-0.57

POSITIVE LOGITS

 anti

1.23

 medication

1.12

 medications

1.08

 antibiotics

1.04

 drugs

1.03

 antidepressants

1.01

 medicines

0.99

 Anti

0.95

 antidepress

0.94

 meds

0.91

Activations Density 0.809%

medical terminology related to treatments and medications

No Comments

No Known Activations