INDEX

Explanations

markers or annotations related to comments and documentation in code

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

Tokens after asterisks or at signs

np_acts-logits-general · gemini-2.0-flash

code comments (`/**`, `//`)

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

GeoNames

-0.73

 تضيفلها

-0.66

gink

-0.58

…’

-0.58

abspath

-0.58

readFileSync

-0.57

><?

-0.56

 kolorze

-0.56

 mergeFrom

-0.56

($__

-0.55

POSITIVE LOGITS

****************

1.12

//*

1.01

0.73

帖最后由

0.73

***********

0.73

0.72

 complètes

0.72

 humain

0.70

{@

0.70

//**

0.69

Activations Density 0.048%

markers or annotations related to comments and documentation in code

Tokens after asterisks or at signs

code comments (`/**`, `//`)

No Comments

No Known Activations