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

 Nicaragua

-0.69

ipop

-0.68

opol

-0.68

owder

-0.67

olesc

-0.65

ulla

-0.64

ament

-0.63

umper

-0.63

acco

-0.62

 Pony

-0.62

POSITIVE LOGITS

 collective

1.15

NECT

0.73

gener

0.71

hedral

0.70

ãĥ¯ãĥ³

0.69

hover

0.68

SourceFile

0.67

Snap

0.67

Balt

0.67

snap

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.