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

arty

-0.75

ffen

-0.70

renched

-0.67

zona

-0.66

inson

-0.65

enei

-0.64

anked

-0.63

rons

-0.63

erto

-0.63

ecast

-0.62

POSITIVE LOGITS

æĪ¦

0.80

fold

0.76

ä¹

0.76

intendent

0.75

Narr

0.73

çļ

0.73

 Annotations

0.72

äº

0.71

CRIP

0.71

english

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.