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

eson

-0.80

aea

-0.77

URA

-0.76

GS

-0.69

awa

-0.68

IU

-0.68

orsche

-0.67

Ws

-0.66

oor

-0.66

oe

-0.65

POSITIVE LOGITS

 Martial

0.79

 Tanz

0.76

quer

0.69

 theirs

0.68

 Aster

0.67

fried

0.66

 marqu

0.66

 yours

0.65

ardy

0.64

 tabl

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.