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

³

-0.88

 Passage

-0.80

ALSE

-0.78

æĸ¹

-0.75

Loading

-0.73

ight

-0.72

IFIED

-0.66

 Voting

-0.62

noon

-0.61

 milestone

-0.61

POSITIVE LOGITS

Äĩ

0.73

pox

0.70

 Tycoon

0.68

artney

0.68

 innovate

0.67

arbon

0.66

azines

0.63

ocaly

0.62

arate

0.62

CPS

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.