INDEX

Explanations

keywords related to nuclear programs or weapons

oai_token-act-pair · gpt-3.5-turbo

references to nuclear programs and weapons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

alach

-0.79

 Orth

-0.78

Thom

-0.75

ifest

-0.75

aird

-0.73

Ort

-0.70

olds

-0.69

Guard

-0.69

 Barber

-0.69

 Hitchcock

-0.69

POSITIVE LOGITS

 weapons

0.93

 warheads

0.92

 enrichment

0.90

 bombs

0.90

 blackmail

0.87

 proliferation

0.86

 dismant

0.86

 bomb

0.84

 missiles

0.84

 missile

0.84

Activations Density 0.040%

keywords related to nuclear programs or weapons

references to nuclear programs and weapons

No Comments

No Known Activations