INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 awaits

-0.70

 awoken

-0.69

ãĥ¯ãĥ³

-0.69

 rounding

-0.68

proof

-0.65

 Bunker

-0.61

numbered

-0.61

Vaj

-0.60

 absorbing

-0.59

 premie

-0.59

POSITIVE LOGITS

arenthood

0.70

imb

0.69

 Cookies

0.69

nis

0.69

itution

0.67

encia

0.67

Performance

0.66

ctica

0.65

 Scrolls

0.64

FN

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.