INDEX

Explanations

elements of JavaScript code related to class definitions and their methods

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

Code-related tokens followed by periods

np_acts-logits-general · gemini-2.0-flash

object properties and methods

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

():

-0.64

calyptic

-0.63

 window

-0.54

 Window

-0.54

gulier

-0.54

 anzu

-0.52

 document

-0.52

 Dokument

-0.52

Date

-0.51

 Affaires

-0.50

POSITIVE LOGITS

RenderAtEndOf

0.88

['

0.69

ValueStyle

0.66

["

0.64

XmlAccessType

0.61

setVerticalGroup

0.59

 defaultstate

0.58

 Савезне

0.56

 OnInit

0.56

enumi

0.56

Activations Density 0.083%

elements of JavaScript code related to class definitions and their methods

Code-related tokens followed by periods

object properties and methods

No Comments

No Known Activations