INDEX

Explanations

phrases related to intense emotions or actions

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 remembrance

-0.72

 lapse

-0.71

 contender

-0.65

 disarm

-0.63

CPC

-0.62

 laure

-0.62

 candle

-0.62

vironment

-0.61

 standby

-0.60

 stale

-0.60

POSITIVE LOGITS

ratch

1.33

ulpt

1.32

rupulous

1.30

apers

1.24

oops

1.23

ouring

1.23

ribe

1.21

opes

1.20

ammers

1.20

rawling

1.19

Activations Density 0.393%

phrases related to intense emotions or actions

No Comments

No Known Activations