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

grave

-0.74

ogle

-0.63

 Rebell

-0.63

 compositions

-0.61

------------------------

-0.59

leck

-0.59

ä½ľ

-0.56

vic

-0.56

eele

-0.56

ihar

-0.56

POSITIVE LOGITS

it

1.22

It

0.90

It

0.89

it

0.85

 away

0.68

unit

0.67

IT

0.67

ratulations

0.63

=[

0.62

itant

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.