INDEX

Explanations

code comments and markup syntax in programming

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

Appears before summary, editor, box, name, or bits

np_acts-logits-general · gemini-2.0-flash

`/// <summary>` and code context

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

Gambas

-0.84

DockStyle

-0.83

 ویکی‌پدی

-0.78

يكب

-0.75

Vidite

-0.74

picasso

-0.71

LinkId

-0.71

 ErrIntOverflow

-0.70

 Italijanski

-0.70

routeProvider

-0.70

POSITIVE LOGITS

summary

0.74

param

0.49

dev

0.49

 mord

0.47

ρίζ

0.47

mär

0.45

 summary

0.44

ThemeProvider

0.44

zor

0.43

 diab

0.43

Activations Density 0.025%

code comments and markup syntax in programming

Appears before summary, editor, box, name, or bits

`/// <summary>` and code context

No Comments

No Known Activations