INDEX

Explanations

references to military exercises and training scenarios

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

"exercise" or "maneuvers" (physical or mental)

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

LabelTagHelper

-0.50

 propOrder

-0.46

 defaultstate

-0.44

Derbyniad

-0.43

AddTagHelper

-0.42

]")]

-0.42

 Normdatei

-0.41

Vorte

-0.41

Autoritní

-0.40

aarrggbb

-0.40

POSITIVE LOGITS

 exercises

2.28

 exercise

2.14

 Exercises

1.91

 Exercise

1.91

exercise

1.84

Exercise

1.83

exercises

1.80

 exercices

1.77

 exerci

1.76

Exercises

1.74

Activations Density 0.116%

references to military exercises and training scenarios

"exercise" or "maneuvers" (physical or mental)

No Comments

No Known Activations