INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

quickShipAvailable

-0.79

Prosecut

-0.76

ities

-0.72

tera

-0.71

Ms

-0.66

Bound

-0.66

soType

-0.66

isSpecialOrderable

-0.66

Mot

-0.64

ascript

-0.64

POSITIVE LOGITS

dash

0.67

brance

0.66

 thirsty

0.66

 wine

0.64

 Anonymous

0.64

rose

0.64

beard

0.61

liness

0.60

agra

0.58

 Bradley

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.