INDEX

Explanations

references to and related to the Roman Empire

oai_token-act-pair · gpt-3.5-turbo

references to the Roman civilization or its related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intosh

-1.14

mble

-1.04

*/(

-0.92

jri

-0.92

NetMessage

-0.91

ramid

-0.91

olulu

-0.86

ilater

-0.82

EStream

-0.81

ickr

-0.80

POSITIVE LOGITS

 Catholic

1.02

 Roman

0.92

 numer

0.89

 Torch

0.86

 Reign

0.85

 Catholicism

0.84

 Catholics

0.81

 Inquisition

0.80

 Emperor

0.79

 Conquest

0.78

Activations Density 0.008%

references to and related to the Roman Empire

references to the Roman civilization or its related concepts

No Comments

No Known Activations