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

ãĥĥãĥĪ

-0.77

ifter

-0.74

à¼

-0.73

ãĤ£

-0.71

ption

-0.68

available

-0.68

 Reserv

-0.67

fund

-0.67

bj

-0.66

POSITIVE LOGITS

 Archdemon

0.64

IPS

0.62

Tus

0.60

angers

0.60

ĸļ

0.58

ghai

0.58

 tigers

0.58

 bats

0.57

 portraits

0.56

ribly

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.