INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

IPM

-0.76

 Westminster

-0.69

 Seym

-0.65

Ott

-0.62

lesiastical

-0.62

 Morg

-0.62

Medic

-0.62

MLA

-0.61

 Colleges

-0.61

DOI

-0.61

POSITIVE LOGITS

gap

0.75

ãĥİ

0.73

nox

0.67

 redes

0.66

gur

0.66

ota

0.65

 await

0.64

 abundantly

0.64

hop

0.64

arte

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.