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

 Premiership

-0.73

Ö¼

-0.71

vable

-0.69

Bok

-0.69

 adolesc

-0.65

 CLSID

-0.64

vor

-0.64

ARP

-0.63

 Harlem

-0.62

AV

-0.62

POSITIVE LOGITS

iencies

0.79

riad

0.74

rawling

0.74

ities

0.72

 share

0.68

 quirks

0.68

erenn

0.66

ivities

0.64

itatively

0.64

othe

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.