INDEX

Explanations

phrases related to violent or deadly incidents

oai_token-act-pair · gpt-3.5-turbo

instances of people being killed in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Favorite

-0.78

enn

-0.75

Bey

-0.74

caster

-0.74

oyer

-0.73

inion

-0.73

$$$$

-0.72

DragonMagazine

-0.72

Completed

-0.72

ESPN

-0.71

POSITIVE LOGITS

 childbirth

1.12

 infancy

1.00

 accidents

0.97

 relation

0.94

 captivity

0.92

 collisions

0.92

 retaliation

0.90

 clashes

0.89

 vain

0.88

 custody

0.88

Activations Density 0.108%

phrases related to violent or deadly incidents

instances of people being killed in various contexts

No Comments

No Known Activations