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

yip

-0.82

 kindred

-0.76

abouts

-0.73

govtrack

-0.69

igr

-0.69

cair

-0.68

aghd

-0.67

 nodd

-0.66

ETHOD

-0.65

 reckoned

-0.65

POSITIVE LOGITS

ARDS

0.70

LEASE

0.67

Tesla

0.65

BD

0.64

HF

0.63

Developer

0.63

 Lenovo

0.63

FT

0.62

leases

0.62

WIN

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.