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

slot

-0.68

Attach

-0.63

 sund

-0.62

 attach

-0.62

il

-0.59

dos

-0.59

sil

-0.59

addons

-0.58

 exiled

-0.58

irit

-0.57

POSITIVE LOGITS

ilogy

0.79

 Parables

0.77

Ö¼

0.76

iosyncr

0.73

elfare

0.73

 Sprite

0.65

 Bride

0.65

cedented

0.64

vana

0.63

itizen

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.