INDEX

Explanations

terms related to healthcare settings and practices

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

WaitGroup

-0.81

 Signalez

-0.71

ConstraintMaker

-0.70

WindowConstants

-0.67

 hospitals

-0.62

 Hospitals

-0.58

 Staging

-0.57

 समीक्षाएं

-0.55

 Règlement

-0.54

 staging

-0.54

POSITIVE LOGITS

 practice

1.19

Practice

1.08

 Practice

1.07

practice

1.03

 office

1.01

 praktijk

0.95

 PRACTICE

0.94

 offices

0.92

office

0.90

PRACTICE

0.87

Activations Density 0.261%

terms related to healthcare settings and practices

No Comments

No Known Activations