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

 renovations

-0.71

ometers

-0.66

opic

-0.65

 revolving

-0.63

geist

-0.62

ãĥ¼ãĥ«

-0.62

opia

-0.62

HIP

-0.61

Kut

-0.61

 squats

-0.60

POSITIVE LOGITS

ser

0.70

enei

0.69

genre

0.68

Synopsis

0.67

plom

0.67

athom

0.66

externalActionCode

0.66

dor

0.66

DragonMagazine

0.65

 undersc

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.