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

inventoryQuantity

-0.87

*/(

-0.70

Website

-0.67

Distance

-0.66

neau

-0.66

idget

-0.65

tm

-0.65

Ñı

-0.65

awaited

-0.65

inates

-0.64

POSITIVE LOGITS

 Cohn

0.76

 Carth

0.73

 Fusion

0.73

 McCain

0.72

 Coulter

0.71

 alum

0.67

 Mount

0.66

 Mazda

0.65

 Morton

0.65

 Reagan

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.