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

ailable

-0.97

addy

-0.82

awaru

-0.74

çīĪ

-0.74

liest

-0.67

idable

-0.67

owned

-0.66

andal

-0.65

ritis

-0.64

chy

-0.64

POSITIVE LOGITS

Foo

0.69

Ala

0.68

 Contra

0.64

 Arbit

0.64

 Mosque

0.63

CU

0.62

£ı

0.62

 Annotations

0.62

 Warm

0.62

Pax

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.