INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Distribut

-0.73

 Gong

-0.65

 Kali

-0.65

Fei

-0.64

 Instruct

-0.62

Neh

-0.62

itive

-0.61

ollah

-0.61

itudes

-0.61

tions

-0.61

POSITIVE LOGITS

 Buckingham

0.82

 elephants

0.74

{"

0.70

 payday

0.67

raped

0.66

ooters

0.64

zsche

0.64

uploads

0.62

 parity

0.61

ampires

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.