INDEX

Explanations

numerical data and statistical results related to scientific studies.

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

phrases related to the biochemistry and function of neurons in the brain.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

citations and reference numbers in scientific text.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

References/citations with bracketed numbers

np_acts-logits-general · gemini-2.0-flash

numbers and symbols in lists

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 الرياضيه

-0.79

脚注の使い方

-0.70

ibrill

-0.68

 nakalista

-0.67

autorest

-0.65

AddTagHelper

-0.64

urlencoded

-0.63

 autorytatywna

-0.63

UMBUS

-0.62

 löyty

-0.62

POSITIVE LOGITS

1.04

contentLoaded

0.52

 continuant

0.46

、

0.42

inerja

0.42

,...

0.41

—

0.41

–

0.38

AxisAlignment

0.36

–