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

aways

-0.74

ways

-0.67

oug

-0.67

resses

-0.65

 Passenger

-0.63

ureau

-0.63

hon

-0.62

oche

-0.60

wrong

-0.60

ibur

-0.60

POSITIVE LOGITS

ILA

0.73

ForgeModLoader

0.73

Ct

0.73

SPONSORED

0.68

Ds

0.67

 Militia

0.66

 dexter

0.65

wu

0.65

lis

0.63

 Puppet

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.