INDEX

Explanations

mentions of people's names

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

uristic

-0.66

afety

-0.63

teness

-0.59

ocaust

-0.58

":"/

-0.58

humane

-0.57

bara

-0.57

ventory

-0.57

rina

-0.57

=/

-0.57

POSITIVE LOGITS

 respectively

2.27

 jointly

1.45

 alike

1.44

 together

1.38

 respective

1.32

 combined

1.29

 mutually

1.25

together

1.19

 Together

1.17

 separately

1.14

Activations Density 6.197%

mentions of people's names

No Comments

No Known Activations