INDEX

Explanations

technical terms related to systems and applications in data management and engineering

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

before "of"

np_acts-logits-general · gemini-2.0-flash

technical terms and abbreviations

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

libft

-0.44

stdc

-0.39

AndEndTag

-0.39

scrapy

-0.36

rizona

-0.35

flashdata

-0.35

SharedDtor

-0.33

bufio

-0.33

NSW

-0.32

POSITIVE LOGITS

 Normdatei

0.86

 يتيمه

0.67

PointerException

0.59

简称

0.57

 (“

0.54

potranspiration

0.52

 kasarigan

0.52

رشف

0.52

ímetros

0.51

fromnode

0.51

Activations Density 1.743%

technical terms related to systems and applications in data management and engineering

before "of"

technical terms and abbreviations

No Comments

No Known Activations