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

adian

-0.75

 Publications

-0.70

omething

-0.68

wine

-0.67

icles

-0.66

antine

-0.65

clerosis

-0.63

bos

-0.62

omnia

-0.62

yrics

-0.62

POSITIVE LOGITS

racuse

0.77

rush

0.73

 gallon

0.64

raq

0.64

uador

0.62

ModLoader

0.62

Mp

0.60

elist

0.60

Ire

0.60

renheit

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.