INDEX

Explanations

words related to facilities, specifically "centers"

oai_token-act-pair · gpt-3.5-turbo

mentions of various types of centers, particularly in a healthcare or service context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ids

-0.71

wcsstore

-0.71

é¾įå

-0.67

ãĤī

-0.64

ãĥīãĥ©

-0.64

--------------------

-0.64

 Bagg

-0.63

IGHTS

-0.61

TON

-0.60

poll

-0.60

POSITIVE LOGITS

 centers

1.22

 centres

1.00

uggest

0.85

bard

0.83

chool

0.81

irtual

0.79

 registers

0.75

 center

0.75

 certific

0.75

pieces

0.75

Activations Density 0.009%

words related to facilities, specifically "centers"

mentions of various types of centers, particularly in a healthcare or service context

No Comments

No Known Activations