INDEX

Explanations

formatted block structures or sections that organize textual information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

lain

-0.83

 McDonnell

-0.71

 Cameron

-0.68

 funn

-0.68

 Xavier

-0.65

alys

-0.65

terday

-0.65

 bearer

-0.65

mallow

-0.63

 Cumber

-0.61

POSITIVE LOGITS

------------

1.35

----------------------------------------------------------------

1.35

--------

1.33

----------------

1.31

-----------

1.31

------------------------------------------------

1.28

------------------------

1.28

-------

1.27

--------------

1.26

---------------

1.25

Activations Density 0.004%

formatted block structures or sections that organize textual information

No Comments

No Known Activations