INDEX

Explanations

references to formal structures or processes within code, including conditions, definitions, and elements related to programming logic

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

Variable tokens or small connector words that serve as functional elements in different types of structured text, including code, formal documents, and formatted content.

eleuther_acts_top20 · claude-3-7-sonnet-20250219 Triggered by @lu-christina

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.78

IBOutlet

-0.78

findpost

-0.68

 IBOutlet

-0.67

Personensuche

-0.67

 ModelExpression

-0.66

Zeneca

-0.65

MessageTagHelper

-0.64

 Paglinawan

-0.64

 AssemblyVersion

-0.63

POSITIVE LOGITS

zusch

0.34

ArrowToggle

0.33

 linkovi

0.30

AddHtmlAttribute

0.29

digkeit

0.28

にあ

0.27

rachtet

0.26

kers

0.26

mentado

0.26

adă

0.25

Activations Density 0.166%

references to formal structures or processes within code, including conditions, definitions, and elements related to programming logic

Variable tokens or small connector words that serve as functional elements in different types of structured text, including code, formal documents, and formatted content.

No Comments

No Known Activations