INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

roid

-0.77

å£«

-0.72

 Robot

-0.69

 Mysteries

-0.69

 Immunity

-0.69

 Robo

-0.68

HQ

-0.66

idge

-0.66

 Dire

-0.65

 Reloaded

-0.64

POSITIVE LOGITS

inav

0.77

jri

0.73

 propriet

0.70

adem

0.70

oters

0.70

 scarcely

0.67

nas

0.66

£ı

0.66

ANC

0.65

erenn

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.