INDEX

Explanations

phrases related to the passage of time

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

uala

-0.74

UA

-0.67

vu

-0.66

vana

-0.64

 Squadron

-0.63

behind

-0.63

ulhu

-0.63

vp

-0.61

Behind

-0.60

fy

-0.60

POSITIVE LOGITS

 weekend

1.03

 course

1.00

 span

0.98

 millennia

0.96

 centuries

0.91

hang

0.88

 decades

0.86

 years

0.83

 holidays

0.81

 hump

0.81

Activations Density 0.518%

phrases related to the passage of time

No Comments

No Known Activations