INDEX

Explanations

phrases related to processes and systems, especially in the context of decision-making and optimization

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

 Defenders

-0.68

OTS

-0.66

ogun

-0.64

TIM

-0.60

Lau

-0.60

 HOUSE

-0.59

Tes

-0.57

RIS

-0.56

 Finder

-0.56

Republic

-0.56

POSITIVE LOGITS

etheless

1.02

ettings

0.89

uyomi

0.86

eday

0.85

erous

0.84

shore

0.83

hett

0.80

SPONSORED

0.79

etime

0.76

eter

0.76

Activations Density 0.016%

phrases related to processes and systems, especially in the context of decision-making and optimization

No Comments

No Known Activations