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

olin

-0.75

wr

-0.75

ritz

-0.72

etting

-0.71

luster

-0.70

ichen

-0.70

hyde

-0.70

PDATE

-0.68

rio

-0.68

nesota

-0.68

POSITIVE LOGITS

 correspond

0.74

VERTISEMENT

0.73

 Diplom

0.69

 Genocide

0.67

 pirates

0.64

 corresponds

0.63

 Customs

0.63

 Arms

0.61

 orcs

0.60

 sweats

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.