INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Redemption

-0.81

=]

-0.78

 Sorce

-0.75

Gaw

-0.73

 Corsair

-0.70

 Starcraft

-0.69

MJ

-0.68

 Merchants

-0.68

caster

-0.67

 McAuliffe

-0.67

POSITIVE LOGITS

ures

0.79

itous

0.78

ure

0.70

erous

0.69

ishes

0.68

rin

0.67

ulously

0.67

ousse

0.64

ortment

0.64

ager

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.