INDEX

Explanations

distinctions or differences between concepts or entities

oai_token-act-pair · gpt-3.5-turbo

phrases related to distinctions or differences between concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

annis

-0.74

rollers

-0.71

vae

-0.70

onz

-0.66

ORE

-0.64

USD

-0.63

odes

-0.63

yrics

-0.62

 paran

-0.62

 Polo

-0.62

POSITIVE LOGITS

naire

1.12

 distinction

0.90

otomy

0.84

erence

0.83

 distinctions

0.81

 between

0.78

 McKenna

0.77

yip

0.76

xual

0.76

ality

0.75

Activations Density 0.025%

distinctions or differences between concepts or entities

phrases related to distinctions or differences between concepts

No Comments

No Known Activations