INDEX

Explanations

occurrences of specific formatting or syntax related to mathematical expressions

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

Mathematical or scientific notation

np_acts-logits-general · gemini-2.0-flash

gauge-fixed field theory

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

StructEnd

-0.63

تقاوى

-0.61

 fieldNum

-0.61

WithIOException

-0.59

GEBURTSDATUM

-0.56

kwds

-0.56

SharedCtor

-0.55

PerformLayout

-0.53

 Chwiliwch

-0.53

titleMargin

-0.52

POSITIVE LOGITS

icose

0.62

出版年

0.56

ροι

0.54

0.53

ianum

0.51

 disponibilités

0.50

ABUL

0.48

ApplicationTests

0.48

bolistas

0.47

jamientos

0.47

Activations Density 0.057%

occurrences of specific formatting or syntax related to mathematical expressions

Mathematical or scientific notation

gauge-fixed field theory

No Comments

No Known Activations