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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Merit

-0.84

lon

-0.76

Recommended

-0.70

Rap

-0.69

Krist

-0.69

ult

-0.69

Joy

-0.68

Limited

-0.67

Asia

-0.66

Lat

-0.65

POSITIVE LOGITS

cules

0.65

ocobo

0.63

afort

0.62

 abroad

0.62

 Aliens

0.62

 uploading

0.62

llah

0.62

romeda

0.60

osponsors

0.60

risome

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.