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

ãĥĵ

-0.74

hung

-0.74

abad

-0.72

ctic

-0.67

CTV

-0.66

Register

-0.65

alian

-0.63

locked

-0.63

SEE

-0.63

audi

-0.61

POSITIVE LOGITS

aution

0.72

 ende

0.70

 conclud

0.69

 Â®

0.68

terness

0.66

oun

0.66

 Cosponsors

0.66

º

0.63

 uphill

0.63

 conflic

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.