INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Knights

-0.68

 Brach

-0.68

imaru

-0.68

ibaba

-0.65

 Emin

-0.63

 Bulg

-0.62

Fei

-0.62

Yen

-0.62

Jou

-0.60

 Clash

-0.60

POSITIVE LOGITS

psc

0.78

 largeDownload

0.78

emis

0.77

raped

0.75

robe

0.74

MpServer

0.74

inventoryQuantity

0.71

ĺħ

0.71

QUI

0.70

Dick

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.