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

ĸļ

-0.93

 zoning

-0.72

 Painter

-0.70

 posting

-0.64

ally

-0.63

 Zimmerman

-0.62

 Europa

-0.62

 Territories

-0.61

 Toledo

-0.60

bound

-0.59

POSITIVE LOGITS

hops

0.67

liber

0.64

thus

0.64

 artif

0.63

 SOFTWARE

0.63

olean

0.62

pring

0.62

 fundament

0.61

alore

0.61

oru

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.