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

 mates

-0.69

 Polic

-0.67

ó

-0.66

 Newman

-0.64

uphem

-0.63

 Slater

-0.63

senal

-0.61

 dehuman

-0.61

 incorpor

-0.60

 Swan

-0.58

POSITIVE LOGITS

umbledore

0.78

ython

0.76

EY

0.75

JECT

0.72

ECA

0.70

dj

0.67

leck

0.66

IES

0.65

 Jace

0.65

deck

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.