INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uminati

-0.80

acters

-0.75

ãĤ¼

-0.72

 Constantin

-0.71

yrights

-0.70

rous

-0.70

ãĥ£

-0.70

yright

-0.70

ortment

-0.69

email

-0.69

POSITIVE LOGITS

 Lung

0.68

GY

0.64

 breathing

0.63

 Nare

0.62

ashi

0.62

 anecd

0.60

itionally

0.60

 Gard

0.60

 Manz

0.59

 grown

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.