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

 Sabha

-0.75

 Sirius

-0.72

 Rite

-0.71

link

-0.69

 Wand

-0.68

 Reset

-0.68

 Beasts

-0.65

 Barbar

-0.63

|--

-0.63

 Simulator

-0.63

POSITIVE LOGITS

qqa

0.81

endez

0.80

ometimes

0.73

Austin

0.73

itivity

0.71

okia

0.71

atform

0.70

acerb

0.70

regon

0.70

atives

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.