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

cade

-0.83

otin

-0.80

 ACPI

-0.80

cus

-0.76

ecause

-0.73

avis

-0.73

ĪĴ

-0.73

nea

-0.72

cedes

-0.70

ierre

-0.68

POSITIVE LOGITS

 capture

0.70

Capture

0.68

RAL

0.65

ãĥ¥

0.64

 Features

0.63

 Caribbean

0.63

 scaven

0.62

 Wanted

0.62

EXP

0.62

ARC

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.