INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

coin

-0.75

oy

-0.70

arnaev

-0.67

gym

-0.66

Coin

-0.66

meal

-0.66

enta

-0.63

eat

-0.63

 trainer

-0.63

sung

-0.62

POSITIVE LOGITS

ID

0.63

icter

0.62

population

0.62

 livest

0.61

 Doctors

0.61

Hos

0.60

 Definitive

0.60

tis

0.59

 Disability

0.59

thumbnails

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.