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

abee

-0.79

rolet

-0.76

untled

-0.71

 marqu

-0.70

 McKay

-0.69

idav

-0.67

 claimant

-0.66

zik

-0.65

gged

-0.64

ŃĶ

-0.63

POSITIVE LOGITS

ilit

0.70

ANG

0.70

natureconservancy

0.68

hist

0.67

wat

0.65

 basil

0.65

rub

0.65

APH

0.65

istries

0.64

apt

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.