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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

estamp

-0.79

laws

-0.72

asin

-0.72

owe

-0.71

ois

-0.67

heon

-0.66

unal

-0.64

âĢ¢âĢ¢

-0.63

 Solitaire

-0.63

late

-0.63

POSITIVE LOGITS

 dams

0.72

 malaria

0.65

 concentrated

0.65

 behavi

0.62

 tremend

0.62

ãĤ¼ãĤ¦ãĤ¹

0.60

 intensive

0.60

 defects

0.60

 submarines

0.59

icular

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.