INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

skirts

-0.68

00200000

-0.67

remlin

-0.64

Buyable

-0.63

 crib

-0.63

 MISS

-0.62

ãĥĻ

-0.61

 Defeat

-0.61

Jet

-0.60

none

-0.59

POSITIVE LOGITS

hra

0.75

pher

0.72

grim

0.72

actionDate

0.70

pter

0.70

irgin

0.68

 Koen

0.68

ierrez

0.68

uth

0.66

oting

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.