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

uyomi

-0.80

yout

-0.78

enment

-0.67

hift

-0.65

ptions

-0.65

mA

-0.64

 Pastebin

-0.63

 GOODMAN

-0.63

CoC

-0.63

ombat

-0.63

POSITIVE LOGITS

akov

0.65

 Nebula

0.64

Availability

0.63

ARGET

0.63

roit

0.62

 Meyer

0.62

×Ļ×

0.61

 Blumenthal

0.60

 Oslo

0.60

ruck

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.