INDEX

Explanations

quotations within the text

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

 favor

-0.82

 parting

-0.81

 slam

-0.80

 pudding

-0.79

 adjud

-0.78

 periodic

-0.74

 brid

-0.74

 classified

-0.74

 prec

-0.74

 powerhouse

-0.74

POSITIVE LOGITS

We

1.59

It

1.59

They

1.56

Because

1.53

1.51

There

1.50

Obviously

1.47

Nobody

1.45

Our

1.44

You

1.44

Activations Density 0.484%

quotations within the text

No Comments

No Known Activations