INDEX

Explanations

strings of numbers like phone numbers or coordinates

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.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

 newsp

-0.66

 firsthand

-0.62

 Ness

-0.59

 existence

-0.55

 compan

-0.55

ASS

-0.53

 trade

-0.52

 overnight

-0.51

 fast

-0.51

 exch

-0.50

POSITIVE LOGITS

1.33

1.31

1.30

1.29

1.28

Activations Density 0.087%

strings of numbers like phone numbers or coordinates

No Comments

No Known Activations