INDEX

Explanations

proper nouns related to individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

minist

-0.90

hire

-0.80

requ

-0.77

-0.75

recomm

-0.75

alez

-0.73

ebook

-0.72

hetical

-0.71

itars

-0.71

rog

-0.71

POSITIVE LOGITS

 Fitzgerald

1.01

 Ellison

0.95

 Summers

0.93

 Kramer

0.92

 Kaufman

0.91

 Wright

0.90

 Petersen

0.89

 Amend

0.84

 Holmes

0.84

 Hogan

0.83

Activations Density 0.020%

proper nouns related to individuals

No Comments

No Known Activations