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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BTC

-0.65

cel

-0.65

arthed

-0.64

 Marina

-0.63

eling

-0.62

dar

-0.62

Maker

-0.60

 Danger

-0.59

 Preservation

-0.59

 Millenn

-0.59

POSITIVE LOGITS

Else

0.78

soever

0.76

aughs

0.71

rawdownloadcloneembedreportprint

0.71

reys

0.67

oggle

0.66

else

0.65

iberal

0.64

VIDIA

0.64

phabet

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.