INDEX

Explanations

references to the Star Trek franchise

oai_token-act-pair · gpt-3.5-turbo

references to the "Star Trek" franchise and its various series and characters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CSS

-0.90

merce

-0.88

iami

-0.86

cig

-0.83

emouth

-0.83

 jQuery

-0.81

 smokers

-0.81

Miami

-0.79

 Cameroon

-0.78

 smoker

-0.77

POSITIVE LOGITS

 Starfleet

1.83

 Klingon

1.71

ajor

1.52

 Spock

1.51

 Kling

1.45

 starship

1.43

 Kira

1.42

 Voyager

1.39

 Picard

1.36

 Trek

1.34

Activations Density 0.201%

references to the Star Trek franchise

references to the "Star Trek" franchise and its various series and characters

No Comments

No Known Activations