INDEX

Explanations

words related to controversial political topics or opinions

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

Negative Logits

FN

-0.70

 Naples

-0.67

 ---------

-0.66

itans

-0.64

 Bulg

-0.64

 Veronica

-0.63

 Winc

-0.63

 Leilan

-0.62

 Machina

-0.60

 Jasper

-0.59

POSITIVE LOGITS

1.21

"-

1.04

"—

1.00

",

1.00

"?

0.99

'?

0.97

"âĢ¦

0.96

"!

0.95

"(

0.92

"'

0.92

Activations Density 0.347%

words related to controversial political topics or opinions

No Known Activations