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

lde

-0.69

 Wooden

-0.68

emouth

-0.67

Ħ¢

-0.65

yard

-0.64

 commons

-0.63

PLIED

-0.61

 Finland

-0.61

tackle

-0.61

yards

-0.59

POSITIVE LOGITS

rates

0.79

rero

0.71

heng

0.71

imen

0.71

DragonMagazine

0.70

hai

0.69

rating

0.66

orsi

0.66

Percent

0.66

astern

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.