INDEX

Explanations

phrases related to work and efforts being made or needed

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

threat

-0.69

 stormed

-0.68

 derog

-0.66

majority

-0.66

 cursed

-0.65

cemic

-0.64

het

-0.63

ethy

-0.63

tall

-0.61

 Warning

-0.60

POSITIVE LOGITS

 done

1.10

 undertaken

1.10

 underway

0.99

 expended

0.97

done

0.89

 performed

0.85

 undone

0.83

umen

0.81

 PROG

0.80

 groundwork

0.80

Activations Density 0.135%

phrases related to work and efforts being made or needed

No Comments

No Known Activations