INDEX

Explanations

German-related entities and names

oai_token-act-pair · gpt-3.5-turbo

references to German newspapers and media outlets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 coral

-1.00

 Baton

-0.91

 Mississ

-0.91

 Korra

-0.90

 Cherokee

-0.87

 Roku

-0.87

 Louisiana

-0.86

 Mayweather

-0.86

 Navajo

-0.84

 coconut

-0.83

POSITIVE LOGITS

 Bundes

1.99

 Germany

1.88

Germany

1.86

 Bundesliga

1.83

 German

1.82

 Munich

1.80

 MÃ¼

1.79

 Berlin

1.76

 Merkel

1.75

 Cologne

1.74

Activations Density 0.832%

German-related entities and names

references to German newspapers and media outlets

No Comments

No Known Activations