INDEX

Explanations

locations/organizations related to political relations and tensions, particularly involving the United States

oai_token-act-pair · gpt-3.5-turbo

references to the city of Washington and its geopolitical implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alach

-0.77

Ont

-0.75

series

-0.75

nutrition

-0.72

Torrent

-0.72

Forest

-0.72

lihood

-0.71

 Tray

-0.70

Gall

-0.70

Loading

-0.69

POSITIVE LOGITS

 policymakers

0.88

 mediated

0.87

 medd

0.87

 bureaucracy

0.87

 meddling

0.85

 deleg

0.85

 diplomats

0.84

 planners

0.82

 propag

0.82

 neocons

0.81

Activations Density 0.077%

locations/organizations related to political relations and tensions, particularly involving the United States

references to the city of Washington and its geopolitical implications

No Comments

No Known Activations