INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 tenant

-0.78

mble

-0.76

 caption

-0.74

reon

-0.74

 expiration

-0.71

uyomi

-0.71

bands

-0.64

deen

-0.64

SPONSORED

-0.64

band

-0.63

POSITIVE LOGITS

romeda

0.86

utions

0.69

 advoc

0.66

iani

0.66

opal

0.65

 Travels

0.64

adv

0.62

 Machina

0.62

TI

0.62

accompan

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.