INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ortium

-0.76

haus

-0.72

 WRITE

-0.72

table

-0.70

 Metatron

-0.68

 Palest

-0.67

 Solitaire

-0.66

 mathemat

-0.66

externalActionCode

-0.66

 Prol

-0.65

POSITIVE LOGITS

agra

0.72

ights

0.72

idency

0.64

ounding

0.63

 living

0.62

urring

0.62

eering

0.62

©¶æ

0.61

 booze

0.61

 bond

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.