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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çīĪ

-0.95

 fixme

-0.68

 Lynch

-0.67

Bei

-0.64

ãĥĲ

-0.63

 Info

-0.62

 vocals

-0.61

 Cinnamon

-0.59

 Moon

-0.59

 Browne

-0.59

POSITIVE LOGITS

anmar

0.98

phrine

0.81

chwitz

0.75

jri

0.75

uterte

0.75

ownt

0.73

idth

0.73

byss

0.73

roleum

0.67

kas

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.