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

ney

-0.70

ospace

-0.68

 Feder

-0.66

optional

-0.65

berra

-0.63

rador

-0.62

 Hanson

-0.62

 Brist

-0.60

 faire

-0.60

agara

-0.60

POSITIVE LOGITS

illet

0.74

ebook

0.70

iosis

0.70

lasses

0.67

andestine

0.65

ores

0.65

umo

0.64

uncle

0.63

aft

0.63

ventures

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.