INDEX

Explanations

political terms and actions

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

ngth

-0.84

ĸļ

-0.80

stress

-0.68

 proble

-0.66

 nerves

-0.64

Course

-0.64

ennes

-0.64

ãĤ¼ãĤ¦ãĤ¹

-0.63

thora

-0.62

æ©Ł

-0.62

POSITIVE LOGITS

 legalizing

1.01

 abolition

0.97

 legalization

0.94

 stricter

0.92

 abol

0.92

 Remain

0.91

 independence

0.90

 repealing

0.90

 secession

0.90

 repeal

0.89

Activations Density 1.406%

political terms and actions

No Comments

No Known Activations