INDEX

Explanations

phrases related to North Korea

oai_token-act-pair · gpt-3.5-turbo

mentions of North Korea and related geopolitical references

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

 "$:/

-0.89

TABLE

-0.83

NRS

-0.77

ulously

-0.75

reviewed

-0.74

natureconservancy

-0.73

TED

-0.73

series

-0.70

="#

-0.70

ATURE

-0.70

POSITIVE LOGITS

 Koreans

1.17

 Korea

1.17

 Korean

0.98

ampton

0.91

uclear

0.87

 Carolina

0.83

 Dakota

0.80

 Pole

0.80

 Kurdistan

0.76

 Jong

0.74

Activations Density 0.027%

phrases related to North Korea

mentions of North Korea and related geopolitical references

No Comments

No Known Activations