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

ordial

-0.78

uscript

-0.74

akespe

-0.72

urally

-0.71

ouver

-0.70

aution

-0.69

orsche

-0.68

ativity

-0.68

anchester

-0.67

umbnails

-0.67

POSITIVE LOGITS

 buds

0.79

é¾įå

0.75

 Messenger

0.72

 Honolulu

0.69

åŃĲ

0.66

Tok

0.66

 Springs

0.64

 Blooming

0.64

çļ

0.64

 circumference

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.