INDEX

Explanations

proper nouns

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_fs12288-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

12,288

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 eleph

-0.89

accompan

-0.83

 teasp

-0.75

 carbohyd

-0.66

 conserv

-0.65

 transitioning

-0.62

 transc

-0.62

 perme

-0.62

 DIRECT

-0.60

 corpor

-0.60

POSITIVE LOGITS

1.17

1.14

1.09

1.02

er

0.98

0.97

ei

0.95

an

0.94

al

0.94

Activations Density 0.282%

proper nouns

No Comments

No Known Activations