INDEX

Explanations

references to military conflict and armed groups

oai_token-act-pair · gpt-3.5-turbo

references to opposition groups within conflict scenarios

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

uckland

-0.95

 Dickens

-0.79

 Lovecraft

-0.77

otrop

-0.77

 Wilde

-0.77

obyl

-0.76

 Compton

-0.75

 Edison

-0.74

keley

-0.73

 Einstein

-0.70

POSITIVE LOGITS

 militias

1.52

 fighters

1.48

 rebels

1.45

 militia

1.31

 insurgents

1.25

 militants

1.24

YPG

1.24

 forces

1.23

 rebel

1.19

 Fighters

1.17

Activations Density 0.199%

references to military conflict and armed groups

references to opposition groups within conflict scenarios

No Comments

No Known Activations