INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

zees

-0.87

 Yamato

-0.78

zee

-0.77

obo

-0.74

rising

-0.68

rored

-0.64

obal

-0.64

zu

-0.63

unks

-0.62

esides

-0.62

POSITIVE LOGITS

EPA

0.81

tml

0.76

è£ħ

0.68

paste

0.64

PLA

0.63

ÃĽ

0.63

 CONT

0.60

 Commodore

0.60

 coli

0.59

 spray

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.