INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ruary

-0.82

skirts

-0.70

Thumbnail

-0.66

 Gust

-0.65

sha

-0.63

ä

-0.62

èĢ

-0.61

èĢħ

-0.59

 Bennett

-0.59

lessness

-0.59

POSITIVE LOGITS

natureconservancy

0.74

afort

0.71

psy

0.70

photos

0.70

osite

0.68

icut

0.67

taboola

0.67

iets

0.67

anmar

0.66

sembly

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.