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

criptions

-0.80

atives

-0.75

acements

-0.74

 expiration

-0.73

 ineligible

-0.71

lam

-0.68

ceivable

-0.68

ours

-0.67

abulary

-0.67

 postponed

-0.66

POSITIVE LOGITS

 Tycoon

0.80

 Pref

0.76

Bot

0.75

 Bots

0.74

 Thing

0.74

 Nanto

0.73

 Leopard

0.71

 Mehran

0.70

 Annotations

0.70

 Readers

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.