INDEX

Explanations

phrases indicating ownership or belonging

oai_token-act-pair · gpt-3.5-turbo

phrases indicating possession or belonging

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

 arrests

-0.74

nel

-0.71

 revolves

-0.70

orah

-0.65

 ende

-0.65

xp

-0.64

ullivan

-0.63

 chilling

-0.62

visor

-0.62

aukee

-0.62

POSITIVE LOGITS

 Sioux

0.68

pees

0.68

 Species

0.66

uton

0.65

 Kant

0.64

utable

0.63

 srfAttach

0.63

 Lank

0.63

 Vander

0.63

 Gong

0.63

Activations Density 0.079%

phrases indicating ownership or belonging

phrases indicating possession or belonging

No Comments

No Known Activations