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

iversary

-0.77

abetes

-0.69

 newsletters

-0.68

ual

-0.67

 Trib

-0.66

afe

-0.66

afety

-0.65

Spons

-0.64

orers

-0.64

 taxable

-0.63

POSITIVE LOGITS

 dumping

0.73

iencies

0.70

¥ŀ

0.69

 conclud

0.68

ATING

0.66

ãĤ¦ãĤ¹

0.66

################

0.66

lid

0.66

 fracturing

0.63

TOR

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.