INDEX

Explanations

events or activities related to workshops, seminars, and symposiums

oai_token-act-pair · gpt-3.5-turbo

references to organized events and workshops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

metics

-0.71

 oily

-0.68

oil

-0.66

 murky

-0.64

agate

-0.63

 thin

-0.62

 proportions

-0.61

é¾įå

-0.61

ãĥĥãĥī

-0.60

 porous

-0.60

POSITIVE LOGITS

 attendees

1.00

 hosted

0.85

goers

0.82

 seminars

0.82

 presentations

0.80

posium

0.80

 sessions

0.78

 attendance

0.77

inar

0.77

pav

0.77

Activations Density 0.241%

events or activities related to workshops, seminars, and symposiums

references to organized events and workshops

No Comments

No Known Activations