INDEX

Explanations

words related to specific locations or organizations, particularly events or financial figures associated with them

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

neys

-0.86

nesday

-0.86

enegger

-0.80

GoldMagikarp

-0.76

tyard

-0.75

kefeller

-0.71

andem

-0.67

auld

-0.67

mercial

-0.67

urtle

-0.66

POSITIVE LOGITS

issance

1.12

utical

1.06

uthor

1.01

eus

0.97

esthesia

0.92

emia

0.89

heim

0.88

vel

0.88

ea

0.87

0.83

Activations Density 0.029%

words related to specific locations or organizations, particularly events or financial figures associated with them

No Comments

No Known Activations