INDEX

Explanations

phrases and content related to interpersonal interactions and social etiquette

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

people or individuals

np_acts-logits-general · gemini-2.0-flash

person or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 AssemblyCulture

-0.64

IntoConstraints

-0.62

发表于

-0.60

RepeatedField

-0.60

haikusbot

-0.54

Vidite

-0.54

 <=",

-0.53

 cref

-0.52

utenants

-0.51

$_['

-0.50

POSITIVE LOGITS

 people

3.04

 person

2.93

people

2.56

 persons

2.53

person

2.36

 Person

2.34

People

2.31

Person

2.27

 personnes

2.23

 People

2.21

Activations Density 0.636%

phrases and content related to interpersonal interactions and social etiquette

people or individuals

person or people

No Comments

No Known Activations