INDEX

Explanations

instructions and advice related to personal preparedness and self-improvement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reconstruction

-0.57

 purported

-0.53

gerald

-0.53

 supplemented

-0.52

Bridge

-0.52

Eastern

-0.51

Ĭ±

-0.51

 Alas

-0.51

 instituted

-0.50

 Vaugh

-0.49

POSITIVE LOGITS

 yourself

1.37

 yourselves

1.16

 Yourself

0.94

 your

0.88

 YOUR

0.74

your

0.70

 Your

0.64

Your

0.64

poke

0.61

omet

0.59

Activations Density 0.412%

instructions and advice related to personal preparedness and self-improvement

No Comments

No Known Activations