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

 moot

-0.66

 tires

-0.64

AFB

-0.64

Mand

-0.60

 Leap

-0.59

EV

-0.57

 Mandela

-0.57

 certs

-0.56

 slang

-0.56

Speaking

-0.55

POSITIVE LOGITS

reenshot

0.79

\/\/

0.79

actionDate

0.77

icas

0.77

encers

0.76

icter

0.76

leased

0.72

ograms

0.71

gotten

0.71

rontal

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.