INDEX

Explanations

phrases related to comparisons, evaluations, and judgments, particularly those indicating degree or extent

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 instead

-0.70

çļ

-0.70

sometimes

-0.68

 periodically

-0.68

probably

-0.66

 nonetheless

-0.66

 rather

-0.65

rather

-0.64

Ĥİ

-0.63

 doubtless

-0.62

POSITIVE LOGITS

 anymore

1.43

 necessarily

1.22

nor

1.08

 bothered

0.97

 anywhere

0.94

 anything

0.88

any

0.88

yet

0.83

 coincidence

0.83

necess

0.82

Activations Density 2.071%

phrases related to comparisons, evaluations, and judgments, particularly those indicating degree or extent

No Comments

No Known Activations