INDEX

Explanations

references to events, introductions, and participants

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

introducing someone or something

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

daz

-0.36

 المعيارى

-0.36

setMinimumSize

-0.34

WriteLiteral

-0.33

 Giant

-0.32

BaseAdapter

-0.32

mk

-0.31

 stores

-0.31

OP

-0.31

 certaines

-0.31

POSITIVE LOGITS

 introductions

0.69

 introductory

0.64

 welcoming

0.61

Introductory

0.61

 greetings

0.61

 introduction

0.60

WELCOME

0.60

 saluto

0.59

introduction

0.58

 salut

0.57

Activations Density 0.009%

references to events, introductions, and participants

introducing someone or something

No Comments

No Known Activations