INDEX

Explanations

phrases related to social issues or political topics

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

assisted

-0.89

OWS

-0.78

breakers

-0.77

anism

-0.75

enance

-0.74

eyes

-0.73

ares

-0.70

chairs

-0.70

tags

-0.69

rates

-0.68

POSITIVE LOGITS

lot

1.28

 tendency

1.22

 possibility

1.21

 shortage

1.19

 plethora

1.16

 definite

1.09

 tremendous

1.03

 chance

1.01

 caveat

1.01

 discrepancy

0.99

Activations Density 0.091%

phrases related to social issues or political topics

No Comments

No Known Activations