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

ahime

-0.91

OTUS

-0.83

NRS

-0.77

oola

-0.76

UL

-0.73

ulative

-0.71

hower

-0.70

tera

-0.69

ÙĴ

-0.69

Øª

-0.67

POSITIVE LOGITS

 Mellon

0.70

 grasping

0.69

 knowing

0.69

 donor

0.68

 Ramsey

0.66

 impunity

0.66

uary

0.66

 orchestr

0.65

 hands

0.64

 strangers

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.