INDEX

Explanations

words related to nuclear weapons and international relations, specifically focusing on discussions about nuclear weapons programs and agreements

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

tyard

-0.81

fil

-0.74

bal

-0.74

haw

-0.73

ful

-0.71

 Agric

-0.70

olds

-0.69

olulu

-0.68

ais

-0.68

 Angeles

-0.67

POSITIVE LOGITS

 warheads

1.01

 missile

1.01

 deton

1.00

 submarine

0.98

 submarines

0.97

 nuclear

0.97

 deterrent

0.96

 reactor

0.95

 uranium

0.95

 radiation

0.91

Activations Density 2.102%

words related to nuclear weapons and international relations, specifically focusing on discussions about nuclear weapons programs and agreements

No Comments

No Known Activations