INDEX

Explanations

mathematical terms related to fractals and set theory

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

 sponsorship

-0.73

 cringe

-0.72

 playbook

-0.72

 catering

-0.70

 elig

-0.70

 invitations

-0.69

 solicitation

-0.69

 Skype

-0.68

 outfits

-0.68

 stewards

-0.68

POSITIVE LOGITS

^{

1.33

\)

1.32

_{

1.22

+(

1.16

=(

1.15

âĪĴ

1.14

)=

1.13

{\

1.11

(-

1.09

{\

1.06

Activations Density 0.729%

mathematical terms related to fractals and set theory

No Comments

No Known Activations