INDEX

Explanations

terms related to philosophical or introspective reflections on life, reality, and society

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

resy

-0.71

 ALSO

-0.70

ciplinary

-0.63

also

-0.59

 Practices

-0.58

 Meanwhile

-0.58

Meanwhile

-0.58

bara

-0.58

ILE

-0.57

endif

-0.55

POSITIVE LOGITS

etc

0.70

 ones

0.62

(),

0.61

or

0.61

Â®,

0.60

asma

0.56

 versus

0.56

 acupuncture

0.56

 yoga

0.55

ttes

0.55

Activations Density 2.903%

terms related to philosophical or introspective reflections on life, reality, and society

No Comments

No Known Activations