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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atten

-0.83

qi

-0.80

plot

-0.78

rise

-0.74

soDeliveryDate

-0.71

Atlanta

-0.71

arthed

-0.70

 Helpful

-0.70

skirts

-0.70

uly

-0.69

POSITIVE LOGITS

 Wolver

0.73

 tant

0.65

 Hearts

0.65

 shorth

0.64

 Guer

0.62

igsaw

0.61

 Schne

0.59

PS

0.58

 Tactical

0.58

 Pound

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.