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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Alien

-0.69

gyn

-0.68

 hyster

-0.67

ãĥĥãĤ¯

-0.65

uary

-0.64

ergy

-0.64

 Halls

-0.62

ĸļ

-0.61

stocks

-0.61

 christ

-0.61

POSITIVE LOGITS

isen

0.73

maximum

0.66

ÅĤ

0.65

riv

0.65

 netted

0.65

ours

0.64

nces

0.64

 Qiao

0.64

Ã¡s

0.64

ult

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.