INDEX

Explanations

phrases related to legal and moral obligations

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

preceding obligations, duties, or responsibilities

np_acts-logits-general · gemini-2.0-flash

duty and responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

parsedMessage

-0.61

NewUrlParser

-0.57

 Seidel

-0.53

 GeoNames

-0.52

verwijspagina

-0.52

oplayer

-0.52

 colorWith

-0.52

XmlAccessorType

-0.50

dafx

-0.50

ThroughAttribute

-0.49

POSITIVE LOGITS

 responsibility

2.38

 duty

2.34

 respon

2.31

 duties

2.30

responsibility

2.05

 obligation

2.04

 Responsibility

1.96

duty

1.94

 obligations

1.91

 Duties

1.88

Activations Density 0.433%

phrases related to legal and moral obligations

preceding obligations, duties, or responsibilities

duty and responsibility

No Comments

No Known Activations