INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 reintrodu

-0.79

 catapult

-0.76

hab

-0.74

 parach

-0.72

 induct

-0.71

 pudding

-0.71

cffff

-0.70

ãĥ¼ãĥĨ

-0.69

 exerc

-0.69

zed

-0.68

POSITIVE LOGITS

ursive

0.81

ouri

0.73

ropolitan

0.71

ustom

0.67

ensical

0.67

ussian

0.65

SPONSORED

0.65

enses

0.65

ortment

0.63

Mesh

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.