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

ahime

-0.81

wcs

-0.79

ulic

-0.76

indust

-0.75

¥ŀ

-0.75

ntil

-0.71

icter

-0.70

ngth

-0.69

uni

-0.66

orously

-0.66

POSITIVE LOGITS

 weakness

0.69

 GOODMAN

0.66

 mism

0.64

.$

0.63

 Radiant

0.62

 Tolkien

0.62

 provoking

0.62

gery

0.60

 trip

0.60

 fortune

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.