INDEX

Explanations

mentions of a specific political figure or government official

oai_token-act-pair · gpt-3.5-turbo

references to political figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Peru

-0.94

 Lima

-0.91

 Zhao

-0.88

Soy

-0.87

 lunar

-0.86

 Tibetan

-0.86

 Lunar

-0.85

ÄŁ

-0.85

 Chilean

-0.85

 Xiaomi

-0.84

POSITIVE LOGITS

NJ

2.23

NJ

2.12

 Christie

2.09

 Newark

1.94

 Rutgers

1.88

 Jersey

1.84

Jer

1.40

 Devils

1.34

 Camden

1.30

Hob

1.29

Activations Density 0.239%

mentions of a specific political figure or government official

references to political figures and events

No Comments

No Known Activations