INDEX

Explanations

phrases indicating attentiveness or monitoring

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

çĶ°

-0.77

Half

-0.70

 disadvant

-0.66

é¾įå¥ĳå£«

-0.66

VIDIA

-0.64

 pathology

-0.61

Compat

-0.61

ibly

-0.60

ļé

-0.60

IER

-0.59

POSITIVE LOGITS

 tabs

0.72

 inbox

0.71

 forwarded

0.69

 Updates

0.66

readable

0.66

lists

0.63

facebook

0.62

uum

0.62

 scrolling

0.60

 reader

0.60

Activations Density 0.021%

phrases indicating attentiveness or monitoring

No Comments

No Known Activations