INDEX

Explanations

significant punctuation marks that denote the end of sentences or sections

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

A period following a section number (typically "2.2." or "2.3.") that appears at the beginning of a new section heading in scientific papers, technical documentation, or academic articles.

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

IFrame

Link

Negative Logits

 فريبيس

-0.82

⟬

-0.82

expandindo

-0.81

rungsseite

-0.79

 queſta

-0.77

 ProtoMessage

-0.76

NameInMap

-0.75

الدراسه

-0.75

Personendaten

-0.75

 ब्रेकडाउन

-0.75

POSITIVE LOGITS

 Simons

0.28

);

0.28

lad

0.27

째

0.27

 steps

0.27

HasKey

0.27

has

0.27

↵

0.26

型

0.26

su

0.25

Activations Density 0.028%

significant punctuation marks that denote the end of sentences or sections

A period following a section number (typically "2.2." or "2.3.") that appears at the beginning of a new section heading in scientific papers, technical documentation, or academic articles.

No Known Activations

significant punctuation marks that denote the end of sentences or sections

A period following a section number (typically "2.2." or "2.3.") that appears at the beginning of a new section heading in scientific papers, technical documentation, or academic articles.

No Known Activations