INDEX

Explanations

technical terms and references related to clinical guidelines and protocols

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

expandindo

-0.93

 disambiguazione

-0.86

 AssemblyCulture

-0.85

aarrggbb

-0.82

ंदीखरीदारी

-0.81

تقاوى

-0.81

parsedMessage

-0.81

ThroughAttribute

-0.78

 المعيارى

-0.76

Hauptartikel

-0.74

POSITIVE LOGITS

 guidelines

1.76

 Guidelines

1.50

 guideline

1.47

guidelines

1.39

Guidelines

1.34

 standards

1.31

 guidance

1.28

 guide

1.23

 Guideline

1.19

 GUIDELINES

1.19

Activations Density 0.642%

technical terms and references related to clinical guidelines and protocols

No Comments

No Known Activations