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

 Runes

-0.78

MIT

-0.74

league

-0.73

Raven

-0.69

 Rune

-0.68

Hoo

-0.68

Ja

-0.67

 Admin

-0.63

Wik

-0.63

eas

-0.63

POSITIVE LOGITS

onica

0.89

 tremend

0.79

ISON

0.77

rians

0.76

¶ħ

0.75

cules

0.74

isons

0.73

ionic

0.73

ighed

0.73

abbage

0.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.