INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

dden

-0.78

 intangible

-0.69

 Creep

-0.66

)</

-0.66

 Mellon

-0.64

 diamonds

-0.64

 Jagu

-0.63

 Rolls

-0.63

 Chau

-0.63

Dug

-0.62

POSITIVE LOGITS

mingham

0.77

McA

0.72

mel

0.71

rontal

0.68

warning

0.68

undown

0.67

elled

0.67

amines

0.66

amine

0.65

broken

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.