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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.94

arty

-0.80

inka

-0.73

perse

-0.72

 Kath

-0.69

ath

-0.68

iste

-0.68

oline

-0.68

aments

-0.68

alam

-0.66

POSITIVE LOGITS

 Pirates

0.75

 Squadron

0.63

Ń·

0.62

 Stream

0.61

umbn

0.61

 Citizens

0.61

 Crusade

0.61

 Reincarnated

0.60

anders

0.59

Geo

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.