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

idine

-0.75

elly

-0.70

lik

-0.68

 malf

-0.68

warts

-0.67

oller

-0.67

urat

-0.66

isine

-0.66

 fled

-0.66

 disapp

-0.65

POSITIVE LOGITS

0.99

MG

0.76

 Butcher

0.70

 Coffin

0.70

 ILCS

0.69

 Fathers

0.67

 Poles

0.65

 Staten

0.64

 Afric

0.64

phe

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.