INDEX

Explanations

phrases indicating when something falls short of expectations or requirements, often used in a critical context

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

uo

-0.76

ellar

-0.75

 origin

-0.74

ale

-0.65

 Disp

-0.65

loc

-0.63

RAW

-0.62

cov

-0.61

ellation

-0.59

CU

-0.59

POSITIVE LOGITS

izabeth

0.91

 miser

0.82

ths

0.82

kat

0.73

terday

0.71

due

0.68

ously

0.67

lust

0.66

 amid

0.66

 because

0.65

Activations Density 0.037%

phrases indicating when something falls short of expectations or requirements, often used in a critical context

No Comments

No Known Activations