INDEX

Explanations

terms related to flowcharting and process documentation

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

Diagrams and flowcharts

np_acts-logits-general · gemini-2.0-flash

diagram, flowchart, organizational charts

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

RetentionPolicy

-0.57

 Betten

-0.56

bandcamp

-0.56

</thead>

-0.54

 Pliny

-0.53

Saber

-0.53

 Gies

-0.53

 Bessel

-0.51

 BoxFit

-0.49

 Kershaw

-0.48

POSITIVE LOGITS

 diagram

1.37

 flowchart

1.19

 diagrams

1.18

diagram

1.08

 flow

1.05

Diagram

1.05

 Diagram

1.05

UML

1.04

 DIAGRAM

0.98

 flows

0.97

Activations Density 0.570%

terms related to flowcharting and process documentation

Diagrams and flowcharts

diagram, flowchart, organizational charts

No Comments

No Known Activations