INDEX

Explanations

phrases and terms related to printing processes and operations

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

"print"

np_acts-logits-general · gemini-2.0-flash

printing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.64

onedDateTime

-0.63

zygous

-0.61

󰀄

-0.58

 Selector

-0.58

ScopeManager

-0.57

jsdelivr

-0.57

 Relic

-0.56

 Seeker

-0.56

 Hetero

-0.56

POSITIVE LOGITS

 print

1.02

print

1.02

Print

1.00

 Print

0.95

 PRINT

0.85

PRINT

0.80

 prints

0.77

 Printing

0.76

Printing

0.76

 printing

0.75

Activations Density 0.054%

phrases and terms related to printing processes and operations

"print"

printing

No Comments

No Known Activations