INDEX

Explanations

statistics and numerical data in written content

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

 nurture

-0.78

²¾

-0.70

NetMessage

-0.69

 proactive

-0.69

 earnest

-0.68

 nurturing

-0.66

 interaction

-0.66

olitical

-0.66

DRM

-0.65

vertisements

-0.65

POSITIVE LOGITS

total

1.10

 averages

1.02

Percent

1.00

 compared

1.00

average

0.99

maximum

0.98

 total

0.97

Total

0.97

 averaged

0.94

Maximum

0.91

Activations Density 3.489%

statistics and numerical data in written content

No Comments

No Known Activations