INDEX

Explanations

forms of the word "end" and its variations, usually related to completion or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rabbit

-0.83

Rac

-0.66

 Chau

-0.65

 Valkyrie

-0.64

 Lack

-0.64

 Beautiful

-0.64

 Rack

-0.63

 Bron

-0.62

Spo

-0.60

CLA

-0.60

POSITIVE LOGITS

ences

0.92

ciating

0.92

agues

0.91

anship

0.90

aults

0.90

acters

0.88

ciation

0.87

ettings

0.86

ents

0.85

ational

0.85

Activations Density 0.122%

forms of the word "end" and its variations, usually related to completion or conclusion

No Comments

No Known Activations