INDEX

Explanations

mentions of specific names and detailed technical information

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

enegger

-1.08

enburg

-0.90

gow

-0.82

ãģ®éŃĶ

-0.79

iants

-0.78

beard

-0.72

omy

-0.70

 Patreon

-0.69

worthiness

-0.68

 Nanto

-0.67

POSITIVE LOGITS

³

1.30

¦

1.14

¹

1.09

 Enix

1.08

¿

1.08

µ

1.08

¥

1.02

¼

1.00

¨

0.99

¾

0.99

Activations Density 0.769%

mentions of specific names and detailed technical information

No Comments

No Known Activations