INDEX

Explanations

variations and forms of the word "po"

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

"Po" followed by a single letter

np_acts-logits-general · gemini-2.0-flash

Po prefixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WebVitals

-0.96

 betweenstory

-0.93

 متعلقه

-0.90

 nakalista

-0.89

例句

-0.88

 للمعارف

-0.86

ResumeLayout

-0.84

AutoScale

-0.83

 autorytatywna

-0.81

StoryboardSegue

-0.81

POSITIVE LOGITS

Po

1.01

Po

0.87

po

0.77

opo

0.74

po

0.72

 По

0.68

По

0.67

PO

0.65

 Pohl

0.64

opo

0.62

Activations Density 0.260%

variations and forms of the word "po"

"Po" followed by a single letter

Po prefixes

No Comments

No Known Activations