INDEX

Explanations

phrases related to conspiracy theories and extremist groups

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

hooting

-0.81

Ĥİ

-0.69

bis

-0.67

HAEL

-0.67

Sport

-0.65

jen

-0.63

Benz

-0.62

 Digest

-0.62

steps

-0.61

 Slowly

-0.61

POSITIVE LOGITS

 knack

1.25

 tendency

1.06

 chance

1.02

 penchant

1.00

 vested

0.93

 capability

0.93

 pedigree

0.92

 flair

0.91

 opportunity

0.90

 affinity

0.89

Activations Density 4.709%

phrases related to conspiracy theories and extremist groups

No Comments

No Known Activations