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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ¥µ

-0.95

etheless

-0.79

nz

-0.74

armac

-0.71

erey

-0.71

Ļ½

-0.69

£ı

-0.69

lost

-0.69

eton

-0.69

ipel

-0.68

POSITIVE LOGITS

inventoryQuantity

0.81

 Clubs

0.71

SourceFile

0.66

 Properties

0.65

essors

0.64

 Sounders

0.63

BCC

0.63

 Pelicans

0.62

 Timbers

0.62

 posit

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.