INDEX

Explanations

words related to living spaces or accommodations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

Data Type

torch.float32

Hook Point

blocks.8.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

PER

-0.81

igslist

-0.80

pheus

-0.80

ĸļ

-0.73

phis

-0.72

urity

-0.72

hedral

-0.66

pson

-0.66

raltar

-0.65

 fram

-0.64

POSITIVE LOGITS

robe

1.15

ragon

0.93

leness

0.88

 Mechdragon

0.86

rums

0.84

hips

0.82

ice

0.80

aign

0.80

ians

0.80

rill

0.79

Activations Density 0.382%

words related to living spaces or accommodations

No Comments

No Known Activations