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

APD

-0.64

 denotes

-0.64

dos

-0.62

ohydrate

-0.62

boxing

-0.62

};

-0.62

æ©Ł

-0.61

};

-0.60

 Duty

-0.60

ãĥ´ãĤ¡

-0.59

POSITIVE LOGITS

obil

0.68

 Gathering

0.65

arious

0.64

Ħ¢

0.63

uzz

0.62

umar

0.62

 Pinball

0.61

rill

0.60

¦

0.59

¤

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.