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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bies

-0.76

biz

-0.72

bent

-0.71

èª

-0.70

spe

-0.68

ãĤ°

-0.68

Austral

-0.68

ãĥ¡

-0.65

aways

-0.65

court

-0.63

POSITIVE LOGITS

umenthal

0.86

usha

0.70

 Gutenberg

0.69

ippi

0.64

ibrary

0.62

 Lowell

0.62

Hub

0.61

 Hiroshima

0.60

 priceless

0.60

amera

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.