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

ideshow

-0.80

usters

-0.75

aints

-0.74

thood

-0.70

idays

-0.70

igil

-0.69

utic

-0.68

ascus

-0.68

phe

-0.67

bane

-0.66

POSITIVE LOGITS

ALLY

0.72

orpor

0.64

>[

0.63

ATT

0.63

 Downloads

0.62

 misinterpret

0.62

GEN

0.62

 Compatibility

0.62

endon

0.61

ERC

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.