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

PokÃ©mon

-0.72

 caut

-0.68

 includ

-0.67

ãĤ¼

-0.66

 mosqu

-0.66

âĵĺ

-0.64

âĶĢâĶĢ

-0.63

 reconciliation

-0.63

 guiActiveUn

-0.62

 mathemat

-0.62

POSITIVE LOGITS

 Stev

0.69

nut

0.67

nuts

0.64

ignty

0.64

kefeller

0.61

 Dread

0.61

uggets

0.60

 Lady

0.60

unci

0.59

fired

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.