INDEX

Explanations

proper nouns and specific details related to events, people, and locations

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

.).

-0.57

}.

-0.55

.</

-0.52

 thereof

-0.51

$.

-0.51

 respectively

-0.48

 guiActiveUnfocused

-0.48

>.

-0.47

 thereto

-0.46

).

-0.45

POSITIVE LOGITS

NBN

0.43

 Canaver

0.42

 Gard

0.38

 OnePlus

0.37

 BahÃ¡

0.35

 Moss

0.35

estern

0.34

 Kund

0.34

 Theft

0.33

yss

0.33

Activations Density 8.942%

proper nouns and specific details related to events, people, and locations

No Comments

No Known Activations