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

Cra

-0.79

Taj

-0.71

 intersections

-0.67

wcs

-0.66

 Destination

-0.65

IGN

-0.64

EC

-0.62

ECA

-0.61

iances

-0.61

rition

-0.60

POSITIVE LOGITS

tower

0.86

æĸ¹

0.78

stad

0.76

Ð¾

0.72

otropic

0.69

)))

0.68

plet

0.66

deen

0.66

gaard

0.64

trop

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.