INDEX

Explanations

mentions of kitchen utensils or appliances, particularly dishwashers

oai_token-act-pair · gpt-3.5-turbo

references to dishes and dishwashers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Armory

-0.77

nesota

-0.68

Gat

-0.67

vernment

-0.67

ICC

-0.65

 Kindle

-0.65

 Ammunition

-0.65

Ops

-0.63

Reviewer

-0.63

 Convention

-0.62

POSITIVE LOGITS

washer

1.91

washing

1.08

ware

1.04

 dishes

0.99

stall

0.92

 dish

0.91

Ingredients

0.91

cloth

0.88

was

0.86

cake

0.85

Activations Density 0.017%

mentions of kitchen utensils or appliances, particularly dishwashers

references to dishes and dishwashers

No Comments

No Known Activations