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

loo

-0.84

PsyNetMessage

-0.74

ourke

-0.69

NetMessage

-0.68

 sudden

-0.65

 undo

-0.65

 Angola

-0.65

AFTA

-0.64

EVA

-0.63

00200000

-0.62

POSITIVE LOGITS

ero

0.71

pn

0.69

stem

0.68

umen

0.65

FIX

0.64

Kid

0.62

chio

0.62

etus

0.61

raph

0.60

ibus

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.