INDEX

Explanations

terms related to law enforcement and legal cases

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

opathic

-0.80

icals

-0.73

arians

-0.68

opathy

-0.66

ICAL

-0.64

 pathology

-0.63

 menstrual

-0.63

 preferential

-0.61

 poisoning

-0.60

Pax

-0.60

POSITIVE LOGITS

mounted

1.28

mount

1.13

fer

1.03

pri

0.95

charge

0.95

lim

0.95

rection

0.95

rend

0.94

geon

0.91

rounded

0.91

Activations Density 0.012%

terms related to law enforcement and legal cases

No Comments

No Known Activations