INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

catentry

-0.75

 Execution

-0.67

zin

-0.66

ENG

-0.64

agascar

-0.63

 Pengu

-0.63

 disag

-0.62

ÃŃs

-0.62

 Pupp

-0.60

 horm

-0.59

POSITIVE LOGITS

ithing

0.66

 Curt

0.65

Around

0.63

mph

0.63

 Carlton

0.62

nm

0.61

liness

0.61

atre

0.61

manship

0.61

ably

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.