INDEX

Explanations

mentions of vacant or vacancy

oai_token-act-pair · gpt-3.5-turbo

terms related to vacancy and unoccupied spaces or positions

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

hran

-0.79

andestine

-0.74

ogue

-0.68

istle

-0.68

pper

-0.68

rid

-0.67

thodox

-0.67

illance

-0.66

plom

-0.65

urai

-0.64

POSITIVE LOGITS

 vacancies

1.20

 vacancy

1.19

 vacant

0.93

 vacated

0.91

©¶æ¥µ

0.82

 listings

0.79

ancies

0.71

 tenancy

0.69

locked

0.68

ãĤ¼ãĤ¦ãĤ¹

0.68

Activations Density 0.007%

mentions of vacant or vacancy

terms related to vacancy and unoccupied spaces or positions

No Comments

No Known Activations