INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

isoft

-0.74

asio

-0.71

agi

-0.69

gers

-0.67

ortality

-0.67

uba

-0.66

erial

-0.66

SIG

-0.65

vernment

-0.62

}:

-0.61

POSITIVE LOGITS

 Chall

0.63

 Subscribe

0.58

 Morty

0.58

 Dare

0.57

 vacancies

0.55

 Bake

0.55

 Advis

0.55

 advisory

0.54

yne

0.54

 attendant

0.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.