INDEX

Explanations

proper nouns appearing in sentences

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ebook

-0.95

arian

-0.94

arians

-0.92

ional

-0.90

expr

-0.86

onal

-0.81

ocre

-0.81

oral

-0.80

unity

-0.80

atories

-0.77

POSITIVE LOGITS

 Mond

1.16

 Reed

0.97

 Winc

0.90

Sob

0.87

 Payton

0.85

 Cron

0.84

 Isaac

0.83

 Walter

0.80

Ley

0.79

Io

0.77

Activations Density 0.013%

proper nouns appearing in sentences

No Comments

No Known Activations