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

 compulsion

-0.73

 inclination

-0.70

 customs

-0.68

 duties

-0.66

RPG

-0.65

 necessity

-0.65

itions

-0.65

 duty

-0.63

psey

-0.63

addon

-0.62

POSITIVE LOGITS

WIN

0.75

cliffe

0.74

[+

0.72

aido

0.67

ippy

0.65

amo

0.64

mble

0.63

ijk

0.62

linger

0.62

itized

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.