INDEX

Explanations

phrases related to willingness or readiness to do something

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

 Compass

-0.79

////////////////////////////////

-0.73

Offline

-0.67

lav

-0.67

soDeliveryDate

-0.66

calling

-0.65

 Thumbnails

-0.64

iens

-0.64

Lear

-0.63

rising

-0.63

POSITIVE LOGITS

 accept

1.39

 admit

1.30

 tolerate

1.28

 cooperate

1.25

 concede

1.20

 give

1.17

 endorse

1.12

 sacrifice

1.11

 participate

1.09

 listen

1.08

Activations Density 0.791%

phrases related to willingness or readiness to do something

No Comments

No Known Activations