INDEX

Explanations

mentions of the word "Pi" and its variations in different contexts

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

starting with "Pi" or "PI"

np_acts-logits-general · gemini-2.0-flash

pi, PI, Pit, Pitt, Piz, Pim, Piper

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

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

раздо

-0.45

ChildScrollView

-0.45

llac

-0.40

UBLE

-0.39

AMS

-0.38

aR

-0.36

lehre

-0.36

hpur

-0.36

DBC

-0.36

SFD

-0.36

POSITIVE LOGITS

aarrggbb

0.62

Pi

0.54

 Пи

0.53

ピ

0.52

 пи

0.52

Piz

0.50

Pim

0.50

Pi

0.50

 Piper

0.50

PIT

0.49

Activations Density 0.225%

mentions of the word "Pi" and its variations in different contexts

starting with "Pi" or "PI"

pi, PI, Pit, Pitt, Piz, Pim, Piper

No Comments

No Known Activations