INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

paio

-0.73

 Jacobs

-0.69

 Stevenson

-0.67

IAS

-0.63

uez

-0.63

 Keystone

-0.62

 JACK

-0.61

iolet

-0.61

everal

-0.61

lease

-0.60

POSITIVE LOGITS

ãĤ¨ãĥ«

0.85

 Creator

0.80

theless

0.72

uru

0.70

ãĥĻ

0.70

å§«

0.69

quickShipAvailable

0.68

arah

0.68

stery

0.67

arus

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.