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

 Glock

-0.72

 Exhibit

-0.65

 Emanuel

-0.63

 pertinent

-0.59

 seam

-0.59

ht

-0.59

 Flor

-0.58

 undercover

-0.58

wcsstore

-0.58

 Cumber

-0.58

POSITIVE LOGITS

sonian

0.85

ORN

0.81

aptic

0.79

/+

0.76

ogyn

0.76

RAW

0.76

++)

0.71

ROM

0.71

Î³

0.68

OSP

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.