INDEX

Explanations

references to nuclear weapons

oai_token-act-pair · gpt-3.5-turbo

references to nuclear weapons and their various contexts and implications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.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

 Barber

-0.81

 Homeless

-0.79

 Martinez

-0.75

Interstitial

-0.74

 Ward

-0.71

Ward

-0.71

 Welsh

-0.70

 Matte

-0.70

Wim

-0.70

 Meyer

-0.69

POSITIVE LOGITS

utonium

1.06

 warheads

1.05

 submarines

1.03

 submarine

0.93

 deton

0.91

 centrif

0.90

 installations

0.88

 detonated

0.87

 stockp

0.87

 readiness

0.86

Activations Density 0.168%

references to nuclear weapons

references to nuclear weapons and their various contexts and implications

No Comments

No Known Activations