INDEX

Explanations

It appears that Neuron 4 does not activate for any of the provided tokens, suggesting that it is not finding what it's looking for in this sample or that the pattern it seeks is not present

oai_token-act-pair · gpt-4-turbo

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

Negative Logits

awa

-0.71

ãĤ´ãĥ³

-0.70

ITNESS

-0.68

£ı

-0.68

isode

-0.67

DragonMagazine

-0.67

clair

-0.67

 Finder

-0.66

 Manifest

-0.66

 Procedures

-0.66

POSITIVE LOGITS

arette

0.81

sle

0.67

 dollar

0.67

enth

0.65

ort

0.64

earch

0.63

idy

0.61

 shop

0.61

 perished

0.60

irm

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.