INDEX

Explanations

statements related to destroying and making safe

oai_token-act-pair · gpt-3.5-turbo

references to destruction and safety in the context of communities or populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 marquee

-0.76

folio

-0.73

NECT

-0.72

 Staples

-0.72

 Oval

-0.71

 BlackBerry

-0.70

Netflix

-0.69

AFTA

-0.69

 Barclays

-0.69

itialized

-0.69

POSITIVE LOGITS

 villagers

1.19

 peasants

1.17

 extermination

1.13

 villages

1.13

 settlers

1.02

 policemen

0.99

 nobles

0.98

 extermin

0.98

 looting

0.97

 bandits

0.97

Activations Density 1.464%

statements related to destroying and making safe

references to destruction and safety in the context of communities or populations

No Comments

No Known Activations