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

dot

-0.69

imm

-0.68

anye

-0.66

Invalid

-0.66

der

-0.65

OX

-0.64

mart

-0.64

EDIT

-0.64

mint

-0.63

uary

-0.62

POSITIVE LOGITS

:{

0.74

izational

0.71

 certs

0.70

 formations

0.69

 campuses

0.68

fleet

0.67

ococ

0.67

achable

0.63

uncture

0.62

ishops

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.