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

atched

-0.78

ERY

-0.78

Eps

-0.67

heast

-0.67

Æ

-0.66

ËĪ

-0.66

Ãĥ

-0.66

apons

-0.66

raised

-0.65

REAM

-0.65

POSITIVE LOGITS

linger

0.77

 Raider

0.66

 spare

0.65

 Unicorn

0.63

erity

0.60

 Thief

0.60

vre

0.59

 Rebels

0.57

 Shiite

0.57

 Blazing

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.