INDEX

Explanations

phrases related to observation or perception

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

 whistle

-0.73

onto

-0.68

inqu

-0.67

nesia

-0.67

eware

-0.66

ÃŃa

-0.64

 agric

-0.63

EStreamFrame

-0.63

trap

-0.62

prime

-0.60

POSITIVE LOGITS

dust

1.18

 firsthand

0.92

 parallels

0.87

awed

0.86

 visions

0.86

lights

0.83

eye

0.83

Ĺ

0.79

fit

0.78

 similarities

0.76

Activations Density 0.514%

phrases related to observation or perception

No Comments

No Known Activations