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

vous

-0.78

çĦ

-0.70

0000000000000000

-0.69

ggle

-0.66

soDeliveryDate

-0.66

TION

-0.65

grass

-0.65

arial

-0.63

bard

-0.62

tis

-0.62

POSITIVE LOGITS

stocks

0.86

 srfAttach

0.68

ertodd

0.63

emic

0.63

aundering

0.63

Mix

0.61

 Trad

0.59

 Button

0.59

stock

0.58

 conglomerate

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.