INDEX

Explanations

references to historical events and locations

oai_token-act-pair · gpt-3.5-turbo

references to historical geopolitical entities and crises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

hun

-0.73

Motor

-0.69

judicial

-0.68

 Somers

-0.66

 diagnostic

-0.66

 Seeking

-0.65

det

-0.64

jog

-0.63

aji

-0.63

 mayoral

-0.63

POSITIVE LOGITS

 USSR

2.54

 Indies

2.06

 Titanic

1.34

 Yugoslavia

1.28

DK

1.24

DK

1.10

 sender

1.07

 Confederacy

1.07

GG

1.04

_>

0.99

Activations Density 0.044%

references to historical events and locations

references to historical geopolitical entities and crises

No Comments

No Known Activations