INDEX

Explanations

references to nuclear weapons and related terms

oai_token-act-pair · gpt-3.5-turbo

references to nuclear weapons and related programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

MpServer

-0.84

idas

-0.83

Urban

-0.77

idav

-0.75

Zip

-0.75

thumbnails

-0.73

lan

-0.73

quickShipAvailable

-0.73

»Ĵ

-0.73

 Levant

-0.73

POSITIVE LOGITS

 plutonium

1.10

 warheads

1.05

 deton

1.00

 dismant

0.97

utonium

0.97

 stockpile

0.96

iferation

0.95

 submarines

0.95

 submarine

0.92

 nuclear

0.92

Activations Density 0.102%

references to nuclear weapons and related terms

references to nuclear weapons and related programs

No Comments

No Known Activations