INDEX

Explanations

phrases related to political discussions and interactions

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

 slic

-0.73

EStreamFrame

-0.68

 annex

-0.67

 tentacles

-0.65

wom

-0.62

 advant

-0.60

 positioning

-0.60

 courier

-0.59

 cone

-0.59

 foreground

-0.59

POSITIVE LOGITS

amorph

1.41

ropolis

1.13

ered

1.07

tle

1.03

ioned

0.93

rose

0.92

onym

0.91

agame

0.86

atars

0.86

alled

0.86

Activations Density 0.024%

phrases related to political discussions and interactions

No Comments

No Known Activations