INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

xi

-0.85

current

-0.71

intosh

-0.71

iliary

-0.70

 Ples

-0.67

puter

-0.66

geist

-0.66

uum

-0.64

oir

-0.63

ioned

-0.62

POSITIVE LOGITS

 Archdemon

0.73

akable

0.72

etooth

0.67

 Wyatt

0.66

ãĤ¼ãĤ¦ãĤ¹

0.62

 Kelley

0.62

 Carly

0.62

Deal

0.61

awar

0.61

 Kurdistan

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.