INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

icion

-0.74

CLOSE

-0.71

aukee

-0.70

 Forge

-0.68

dimension

-0.66

 Springfield

-0.65

 Dayton

-0.64

 Infinity

-0.63

Â·Â·

-0.62

ãĥ³ãĤ¸

-0.61

POSITIVE LOGITS

TAG

0.72

 wallet

0.68

jriwal

0.66

 ashamed

0.66

uphem

0.64

essage

0.63

galitarian

0.62

 advising

0.62

 congratulations

0.61

 worthless

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.