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

erella

-0.88

fet

-0.66

ocene

-0.66

 Tibetan

-0.64

owell

-0.64

tu

-0.64

ofer

-0.62

tan

-0.61

 Jude

-0.61

 tuber

-0.60

POSITIVE LOGITS

alions

0.74

issance

0.70

REP

0.66

IGH

0.66

 GOODMAN

0.65

enced

0.65

IJ

0.65

éĹĺ

0.65

ELY

0.63

dash

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.