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

 disadvant

-0.93

 agre

-0.75

 brill

-0.70

adium

-0.70

 libel

-0.67

=-=-=-=-=-=-=-=-

-0.66

 Citation

-0.66

iasis

-0.65

 compr

-0.65

ivo

-0.65

POSITIVE LOGITS

een

0.69

dit

0.69

flies

0.67

agy

0.67

istries

0.66

friend

0.65

secret

0.65

DEM

0.64

sty

0.64

coded

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.