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

ument

-0.74

ohyd

-0.73

isma

-0.72

CTV

-0.69

redo

-0.66

ossal

-0.66

assetsadobe

-0.65

acial

-0.64

justice

-0.64

gow

-0.64

POSITIVE LOGITS

IRD

0.72

 itch

0.67

atos

0.67

ãĥĻ

0.65

ow

0.64

 Somers

0.64

>>>>>>>>

0.64

 Reaper

0.63

elin

0.62

ãĥĦ

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.