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

naires

-0.69

tty

-0.68

 onboard

-0.67

ilk

-0.66

bin

-0.64

ti

-0.62

 Tibetan

-0.60

ta

-0.58

 Loll

-0.58

hern

-0.57

POSITIVE LOGITS

 Seym

0.79

vertisement

0.76

 defe

0.76

DragonMagazine

0.74

stood

0.72

velength

0.72

quartered

0.71

Effective

0.70

comed

0.70

igmatic

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.