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

ucc

-0.83

ng

-0.78

nw

-0.76

FK

-0.70

gain

-0.69

odge

-0.68

atching

-0.66

agy

-0.65

ULAR

-0.65

addons

-0.65

POSITIVE LOGITS

antha

0.74

 gobl

0.69

 vulner

0.69

 certific

0.69

iola

0.68

roman

0.67

 Aviv

0.67

 demographics

0.66

chart

0.66

encrypted

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.