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

lander

-0.76

chance

-0.76

ãĥ¼ãĥĨ

-0.69

 Monstrous

-0.66

 Cous

-0.64

ãĥ³ãĤ¸

-0.64

 Darling

-0.63

 Maid

-0.63

 Neighbor

-0.63

ghost

-0.63

POSITIVE LOGITS

uria

0.71

ggles

0.68

 distingu

0.68

alore

0.65

umbledore

0.65

ativity

0.64

":"","

0.64

ifications

0.64

\":

0.63

itars

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.