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

WithNo

-0.85

FactoryReloaded

-0.76

CVE

-0.73

heimer

-0.69

mosp

-0.69

TIT

-0.68

 halftime

-0.67

manship

-0.66

 Authorization

-0.65

 sanct

-0.65

POSITIVE LOGITS

lyak

0.84

ellar

0.79

brates

0.75

ãĥ¼ãĥ«

0.75

eva

0.68

ographies

0.66

²¾

0.66

 successors

0.66

 slate

0.66

Ñĭ

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.