INDEX

Explanations

terms related to diagnostic performance metrics and medical analytics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 שוליים

-0.60

KommentareTeilen

-0.59

RTLD

-0.57

principalTable

-0.54

 onCancelled

-0.51

 виправивши

-0.50

WireFormatLite

-0.49

Ծանոթ

-0.49

 EconPapers

-0.48

GraphicsUnit

-0.47

POSITIVE LOGITS

 percentage

1.12

 percentages

1.06

 percent

1.04

(%)

1.04

Percentage

1.03

percent

1.01

 Percentage

1.01

Percent

1.00

 Percent

1.00

percentage

0.97

Activations Density 1.210%

terms related to diagnostic performance metrics and medical analytics

No Comments

No Known Activations