INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 ages

-0.68

 moisture

-0.66

 compiling

-0.63

eh

-0.63

 thinner

-0.63

 berth

-0.63

 sulfur

-0.62

 Carney

-0.62

urchase

-0.60

olean

-0.59

POSITIVE LOGITS

Seg

0.78

atars

0.78

hello

0.71

SPONSORED

0.70

rupt

0.70

look

0.70

MC

0.69

lar

0.68

externalActionCode

0.68

arching

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.