INDEX

Explanations

words related to horror or violence in movies

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ãģ¦

-0.80

 Leilan

-0.74

ãģ®éŃĶ

-0.72

ħĭ

-0.69

anwhile

-0.68

 vigorously

-0.64

eer

-0.64

 graded

-0.62

OHN

-0.61

0000000000000000

-0.60

POSITIVE LOGITS

izontal

1.43

izont

1.37

izons

1.35

rible

1.32

izon

1.20

rors

1.19

ribly

1.16

cru

1.14

ror

1.13

oscope

1.13

Activations Density 0.021%

words related to horror or violence in movies

No Comments

No Known Activations